2024 |
Iranzo-Sánchez, Javier; Iranzo-Sánchez, Jorge; Giménez, Adrià; Civera, Jorge; Juan, Alfons Segmentation-Free Streaming Machine Translation Journal Article Forthcoming Transactions of the Association for Computational Linguistics, 12 , Forthcoming, (also accepted for presentation at ACL 2024). Abstract | Links | BibTeX | Tags: segmentation-free, streaming machine translation @article{Juan2024, title = {Segmentation-Free Streaming Machine Translation}, author = {Javier Iranzo-Sánchez AND Jorge Iranzo-Sánchez AND Adrià Giménez AND Jorge Civera AND Alfons Juan}, url = {https://arxiv.org/abs/2309.14823 https://2024.aclweb.org/program/tacl_papers/ https://www.mllp.upv.es/wp-content/uploads/2024/09/tacl_segfree_poster.pdf https://paperswithcode.com/paper/segmentation-free-streaming-machine https://github.com/jairsan/Segmentation-Free_Streaming_Machine_Translation}, year = {2024}, date = {2024-01-01}, journal = {Transactions of the Association for Computational Linguistics}, volume = {12}, abstract = {Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance.}, note = {also accepted for presentation at ACL 2024}, keywords = {segmentation-free, streaming machine translation}, pubstate = {forthcoming}, tppubtype = {article} } Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance. |
2022 |
Pérez González de Martos, Alejandro ; Giménez Pastor, Adrià ; Jorge Cano, Javier ; Iranzo-Sánchez, Javier; Silvestre-Cerdà, Joan Albert; Garcés Díaz-Munío, Gonçal V; Baquero-Arnal, Pau; Sanchis Navarro, Alberto ; Civera Sáiz, Jorge ; Juan Ciscar, Alfons ; Turró Ribalta, Carlos Doblaje automático de vídeo-charlas educativas en UPV[Media] Inproceedings Proc. of VIII Congrés d'Innovació Educativa i Docència en Xarxa (IN-RED 2022), pp. 557–570, València (Spain), 2022. Abstract | Links | BibTeX | Tags: automatic dubbing, Automatic Speech Recognition, Machine Translation, OER, text-to-speech @inproceedings{deMartos2022, title = {Doblaje automático de vídeo-charlas educativas en UPV[Media]}, author = {Pérez González de Martos, Alejandro AND Giménez Pastor, Adrià AND Jorge Cano, Javier AND Javier Iranzo-Sánchez AND Joan Albert Silvestre-Cerdà AND Garcés Díaz-Munío, Gonçal V. AND Pau Baquero-Arnal AND Sanchis Navarro, Alberto AND Civera Sáiz, Jorge AND Juan Ciscar, Alfons AND Turró Ribalta, Carlos}, doi = {10.4995/INRED2022.2022.15844}, year = {2022}, date = {2022-01-01}, booktitle = {Proc. of VIII Congrés d'Innovació Educativa i Docència en Xarxa (IN-RED 2022)}, pages = {557--570}, address = {València (Spain)}, abstract = {More and more universities are banking on the production of digital content to support online or blended learning in higher education. Over the last years, the MLLP research group has been working closely with the UPV's ASIC media services in order to enrich educational multimedia resources through the application of natural language processing technologies including automatic speech recognition, machine translation and text-to-speech. In this work, we present the steps that are being followed for the comprehensive translation of these materials, specifically through (semi-)automatic dubbing by making use of state-of-the-art speaker-adaptive text-to-speech technologies.}, keywords = {automatic dubbing, Automatic Speech Recognition, Machine Translation, OER, text-to-speech}, pubstate = {published}, tppubtype = {inproceedings} } More and more universities are banking on the production of digital content to support online or blended learning in higher education. Over the last years, the MLLP research group has been working closely with the UPV's ASIC media services in order to enrich educational multimedia resources through the application of natural language processing technologies including automatic speech recognition, machine translation and text-to-speech. In this work, we present the steps that are being followed for the comprehensive translation of these materials, specifically through (semi-)automatic dubbing by making use of state-of-the-art speaker-adaptive text-to-speech technologies. |
Iranzo-Sánchez, Javier; Jorge, Javier; Pérez-González-de-Martos, Alejandro; Giménez, Adrià; Garcés Díaz-Munío, Gonçal V; Baquero-Arnal, Pau; Silvestre-Cerdà, Joan Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks Inproceedings Proc. of 19th Intl. Workshop on Spoken Language Translation (IWSLT 2022), pp. 255–264, Dublin (Ireland), 2022. Abstract | Links | BibTeX | Tags: Simultaneous Speech Translation, speech-to-speech translation @inproceedings{Iranzo-Sánchez2022b, title = {MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks}, author = {Javier Iranzo-Sánchez and Javier Jorge and Alejandro Pérez-González-de-Martos and Adrià Giménez and Garcés Díaz-Munío, Gonçal V. and Pau Baquero-Arnal and Joan Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchis and Alfons Juan}, doi = {10.18653/v1/2022.iwslt-1.22}, year = {2022}, date = {2022-01-01}, booktitle = {Proc. of 19th Intl. Workshop on Spoken Language Translation (IWSLT 2022)}, pages = {255--264}, address = {Dublin (Ireland)}, abstract = {This work describes the participation of the MLLP-VRAIN research group in the two shared tasks of the IWSLT 2022 conference: Simultaneous Speech Translation and Speech-to-Speech Translation. We present our streaming-ready ASR, MT and TTS systems for Speech Translation and Synthesis from English into German. Our submission combines these systems by means of a cascade approach paying special attention to data preparation and decoding for streaming inference.}, keywords = {Simultaneous Speech Translation, speech-to-speech translation}, pubstate = {published}, tppubtype = {inproceedings} } This work describes the participation of the MLLP-VRAIN research group in the two shared tasks of the IWSLT 2022 conference: Simultaneous Speech Translation and Speech-to-Speech Translation. We present our streaming-ready ASR, MT and TTS systems for Speech Translation and Synthesis from English into German. Our submission combines these systems by means of a cascade approach paying special attention to data preparation and decoding for streaming inference. |
Baquero-Arnal, Pau; Jorge, Javier; Giménez, Adrià; Iranzo-Sánchez, Javier; Pérez-González-de-Martos, Alejandro; Garcés Díaz-Munío, Gonçal V; Silvestre-Cerdà, Joan Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge: Extension Journal Article Applied Sciences, 12 (2), pp. 804, 2022. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Natural Language Processing, streaming @article{applsci1505192, title = {MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge: Extension}, author = {Pau Baquero-Arnal and Javier Jorge and Adrià Giménez and Javier Iranzo-Sánchez and Alejandro Pérez-González-de-Martos and Garcés Díaz-Munío, Gonçal V. and Joan Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchis and Alfons Juan}, doi = {10.3390/app12020804}, year = {2022}, date = {2022-01-01}, journal = {Applied Sciences}, volume = {12}, number = {2}, pages = {804}, abstract = {This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politècnica de València for the Albayzín-RTVE 2020 Speech-to-Text Challenge, and includes an extension of the work consisting in building and evaluating equivalent systems under the closed data conditions from the 2018 challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid ASR system using streaming one-pass decoding with a context window of 1.5 seconds. This system achieved 16.0% WER on the test-2020 set. We also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t which, following a similar configuration as the primary system with a smaller context window of 0.6 s, scored 16.9% WER points on the same test set, with a measured empirical latency of 0.81±0.09 seconds (mean±stdev). That is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. As an extension, the equivalent closed-condition systems obtained 23.3% WER and 23.5% WER respectively. When evaluated with an unconstrained language model, we obtained 19.9% WER and 20.4% WER; i.e., not far behind the top-performing systems with only 5% of the full acoustic data and with the extra ability of being streaming-capable. Indeed, all of these streaming systems could be put into production environments for automatic captioning of live media streams.}, keywords = {Automatic Speech Recognition, Natural Language Processing, streaming}, pubstate = {published}, tppubtype = {article} } This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politècnica de València for the Albayzín-RTVE 2020 Speech-to-Text Challenge, and includes an extension of the work consisting in building and evaluating equivalent systems under the closed data conditions from the 2018 challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid ASR system using streaming one-pass decoding with a context window of 1.5 seconds. This system achieved 16.0% WER on the test-2020 set. We also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t which, following a similar configuration as the primary system with a smaller context window of 0.6 s, scored 16.9% WER points on the same test set, with a measured empirical latency of 0.81±0.09 seconds (mean±stdev). That is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. As an extension, the equivalent closed-condition systems obtained 23.3% WER and 23.5% WER respectively. When evaluated with an unconstrained language model, we obtained 19.9% WER and 20.4% WER; i.e., not far behind the top-performing systems with only 5% of the full acoustic data and with the extra ability of being streaming-capable. Indeed, all of these streaming systems could be put into production environments for automatic captioning of live media streams. |
2021 |
Jorge, Javier ; Giménez, Adrià ; Silvestre-Cerdà, Joan Albert ; Civera, Jorge ; Sanchis, Albert ; Alfons, Juan Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models Journal Article IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30 , pp. 148–161, 2021. Abstract | Links | BibTeX | Tags: acoustic modelling, Automatic Speech Recognition, decoding, language modelling, neural networks, streaming @article{Jorge2021b, title = {Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models}, author = {Jorge, Javier and Giménez, Adrià and Silvestre-Cerdà, Joan Albert and Civera, Jorge and Sanchis, Albert and Juan Alfons}, doi = {10.1109/TASLP.2021.3133216}, year = {2021}, date = {2021-11-23}, journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing}, volume = {30}, pages = {148--161}, abstract = {Although Long-Short Term Memory (LSTM) networks and deep Transformers are now extensively used in offline ASR, it is unclear how best offline systems can be adapted to work with them under the streaming setup. After gaining considerable experience in this regard in recent years, in this paper we show how an optimized, low-latency streaming decoder can be built in which bidirectional LSTM acoustic models, together with general interpolated language models, can be nicely integrated with minimal perfomance degradation. In brief, our streaming decoder consists of a one-pass, real-time search engine relying on a limited-duration window sliding over time and a number of ad hoc acoustic and language model pruning techniques. Extensive empirical assessment is provided on truly streaming tasks derived from the well-known LibriSpeech and TED talks datasets, as well as from TV shows from a large Spanish broadcasting station.}, keywords = {acoustic modelling, Automatic Speech Recognition, decoding, language modelling, neural networks, streaming}, pubstate = {published}, tppubtype = {article} } Although Long-Short Term Memory (LSTM) networks and deep Transformers are now extensively used in offline ASR, it is unclear how best offline systems can be adapted to work with them under the streaming setup. After gaining considerable experience in this regard in recent years, in this paper we show how an optimized, low-latency streaming decoder can be built in which bidirectional LSTM acoustic models, together with general interpolated language models, can be nicely integrated with minimal perfomance degradation. In brief, our streaming decoder consists of a one-pass, real-time search engine relying on a limited-duration window sliding over time and a number of ad hoc acoustic and language model pruning techniques. Extensive empirical assessment is provided on truly streaming tasks derived from the well-known LibriSpeech and TED talks datasets, as well as from TV shows from a large Spanish broadcasting station. |
Pérez, Alejandro; Garcés Díaz-Munío, Gonçal ; Giménez, Adrià; Silvestre-Cerdà, Joan Albert ; Sanchis, Albert; Civera, Jorge; Jiménez, Manuel; Turró, Carlos; Juan, Alfons Towards cross-lingual voice cloning in higher education Journal Article Engineering Applications of Artificial Intelligence, 105 , pp. 104413, 2021. Abstract | Links | BibTeX | Tags: cross-lingual voice conversion, educational resources, multilinguality, OER, text-to-speech @article{Pérez2021, title = {Towards cross-lingual voice cloning in higher education}, author = {Alejandro Pérez and Garcés Díaz-Munío, Gonçal and Adrià Giménez and Silvestre-Cerdà, Joan Albert and Albert Sanchis and Jorge Civera and Manuel Jiménez and Carlos Turró and Alfons Juan}, url = {https://doi.org/10.1016/j.engappai.2021.104413}, year = {2021}, date = {2021-10-01}, journal = {Engineering Applications of Artificial Intelligence}, volume = {105}, pages = {104413}, abstract = {The rapid progress of modern AI tools for automatic speech recognition and machine translation is leading to a progressive cost reduction to produce publishable subtitles for educational videos in multiple languages. Similarly, text-to-speech technology is experiencing large improvements in terms of quality, flexibility and capabilities. In particular, state-of-the-art systems are now capable of seamlessly dealing with multiple languages and speakers in an integrated manner, thus enabling lecturer's voice cloning in languages she/he might not even speak. This work is to report the experience gained on using such systems at the Universitat Politècnica de València (UPV), mainly as a guidance for other educational organizations willing to conduct similar studies. It builds on previous work on the UPV's main repository of educational videos, MediaUPV, to produce multilingual subtitles at scale and low cost. Here, a detailed account is given on how this work has been extended to also allow for massive machine dubbing of MediaUPV. This includes collecting 59 hours of clean speech data from UPV’s academic staff, and extending our production pipeline of subtitles with a state-of-the-art multilingual and multi-speaker text-to-speech system trained from the collected data. Our main result comes from an extensive, subjective evaluation of this system by lecturers contributing to data collection. In brief, it is shown that text-to-speech technology is not only mature enough for its application to MediaUPV, but also needed as soon as possible by students to improve its accessibility and bridge language barriers.}, keywords = {cross-lingual voice conversion, educational resources, multilinguality, OER, text-to-speech}, pubstate = {published}, tppubtype = {article} } The rapid progress of modern AI tools for automatic speech recognition and machine translation is leading to a progressive cost reduction to produce publishable subtitles for educational videos in multiple languages. Similarly, text-to-speech technology is experiencing large improvements in terms of quality, flexibility and capabilities. In particular, state-of-the-art systems are now capable of seamlessly dealing with multiple languages and speakers in an integrated manner, thus enabling lecturer's voice cloning in languages she/he might not even speak. This work is to report the experience gained on using such systems at the Universitat Politècnica de València (UPV), mainly as a guidance for other educational organizations willing to conduct similar studies. It builds on previous work on the UPV's main repository of educational videos, MediaUPV, to produce multilingual subtitles at scale and low cost. Here, a detailed account is given on how this work has been extended to also allow for massive machine dubbing of MediaUPV. This includes collecting 59 hours of clean speech data from UPV’s academic staff, and extending our production pipeline of subtitles with a state-of-the-art multilingual and multi-speaker text-to-speech system trained from the collected data. Our main result comes from an extensive, subjective evaluation of this system by lecturers contributing to data collection. In brief, it is shown that text-to-speech technology is not only mature enough for its application to MediaUPV, but also needed as soon as possible by students to improve its accessibility and bridge language barriers. |
Jorge, Javier; Giménez, Adrià; Baquero-Arnal, Pau; Iranzo-Sánchez, Javier; Pérez-González-de-Martos, Alejandro; Garcés Díaz-Munío, Gonçal V; Silvestre-Cerdà, Joan Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge Inproceedings Proc. of IberSPEECH 2021, pp. 118–122, Valladolid (Spain), 2021. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Natural Language Processing, streaming @inproceedings{Jorge2021, title = {MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge}, author = {Javier Jorge and Adrià Giménez and Pau Baquero-Arnal and Javier Iranzo-Sánchez and Alejandro Pérez-González-de-Martos and Garcés Díaz-Munío, Gonçal V. and Joan Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchis and Alfons Juan}, doi = {10.21437/IberSPEECH.2021-25}, year = {2021}, date = {2021-03-24}, booktitle = {Proc. of IberSPEECH 2021}, pages = {118--122}, address = {Valladolid (Spain)}, abstract = {1st place in IberSpeech-RTVE 2020 TV Speech-to-Text Challenge. [EN] This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politecnica de València for the Albayzin-RTVE 2020 Speech-to-Text Challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid BLSTM-HMM ASR system using streaming one-pass decoding with a context window of 1.5 seconds and a linear combination of an n-gram, a LSTM, and a Transformer language model (LM). The acoustic model was trained on nearly 4,000 hours of speech data from different sources, using the MLLP's transLectures-UPV toolkit (TLK) and TensorFlow; whilst LMs were trained using SRILM (n-gram), CUED-RNNLM (LSTM) and Fairseq (Transformer), with up to 102G tokens. This system achieved 11.6% and 16.0% WER on the test-2018 and test-2020 sets, respectively. As it is streaming-enabled, it could be put into production environments for automatic captioning of live media streams, with a theoretical delay of 1.5 seconds. Along with the primary system, we also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t that, following the same configuration of the primary one, but using a smaller context window of 0.6 seconds and a Transformer LM, scored 12.3% and 16.9% WER points respectively on the same test sets, with a measured empirical latency of 0.81+-0.09 seconds (mean+-stdev). This is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. [CA] "Sistemes de reconeixement automàtic de la parla en castellà de MLLP-VRAIN per a la competició Albayzin-RTVE 2020 Speech-To-Text Challenge": En aquest article, es descriuen els sistemes de reconeixement automàtic de la parla (RAP) creats pel grup d'investigació MLLP-VRAIN de la Universitat Politecnica de València per a la competició Albayzin-RTVE 2020 Speech-to-Text Challenge. El sistema primari (p-streaming_1500ms_nlt) és un sistema de RAP híbrid BLSTM-HMM amb descodificació en temps real en una passada amb una finestra de context d'1,5 segons i una combinació lineal de models de llenguatge (ML) d'n-grames, LSTM i Transformer. El model acústic s'ha entrenat amb vora 4000 hores de parla transcrita de diferents fonts, usant el transLectures-UPV toolkit (TLK) del grup MLLP i TensorFlow; mentre que els ML s'han entrenat amb SRILM (n-grames), CUED-RNNLM (LSTM) i Fairseq (Transformer), amb 102G paraules (tokens). Aquest sistema ha obtingut 11,6 % i 16,0 % de WER en els conjunts test-2018 i test-2020, respectivament. És un sistema amb capacitat de temps real, que pot desplegar-se en producció per a subtitulació automàtica de fluxos audiovisuals en directe, amb un retard teòric d'1,5 segons. A banda del sistema primari, s'han presentat tres sistemes contrastius. D'aquests, destaquem el sistema c2-streaming_600ms_t que, amb la mateixa configuració que el sistema primari, però amb una finestra de context més reduïda de 0,6 segons i un ML Transformer, ha obtingut 12,3 % i 16,9 % de WER, respectivament, sobre els mateixos conjunts, amb una latència empírica mesurada de 0,81+-0,09 segons (mitjana+-desv). És a dir, s'han obtingut latències punteres per a subtitulació automàtica en directe d'alta qualitat amb una degradació del WER petita, del 6 % relatiu.}, keywords = {Automatic Speech Recognition, Natural Language Processing, streaming}, pubstate = {published}, tppubtype = {inproceedings} } 1st place in IberSpeech-RTVE 2020 TV Speech-to-Text Challenge. [EN] This paper describes the automatic speech recognition (ASR) systems built by the MLLP-VRAIN research group of Universitat Politecnica de València for the Albayzin-RTVE 2020 Speech-to-Text Challenge. The primary system (p-streaming_1500ms_nlt) was a hybrid BLSTM-HMM ASR system using streaming one-pass decoding with a context window of 1.5 seconds and a linear combination of an n-gram, a LSTM, and a Transformer language model (LM). The acoustic model was trained on nearly 4,000 hours of speech data from different sources, using the MLLP's transLectures-UPV toolkit (TLK) and TensorFlow; whilst LMs were trained using SRILM (n-gram), CUED-RNNLM (LSTM) and Fairseq (Transformer), with up to 102G tokens. This system achieved 11.6% and 16.0% WER on the test-2018 and test-2020 sets, respectively. As it is streaming-enabled, it could be put into production environments for automatic captioning of live media streams, with a theoretical delay of 1.5 seconds. Along with the primary system, we also submitted three contrastive systems. From these, we highlight the system c2-streaming_600ms_t that, following the same configuration of the primary one, but using a smaller context window of 0.6 seconds and a Transformer LM, scored 12.3% and 16.9% WER points respectively on the same test sets, with a measured empirical latency of 0.81+-0.09 seconds (mean+-stdev). This is, we obtained state-of-the-art latencies for high-quality automatic live captioning with a small WER degradation of 6% relative. [CA] "Sistemes de reconeixement automàtic de la parla en castellà de MLLP-VRAIN per a la competició Albayzin-RTVE 2020 Speech-To-Text Challenge": En aquest article, es descriuen els sistemes de reconeixement automàtic de la parla (RAP) creats pel grup d'investigació MLLP-VRAIN de la Universitat Politecnica de València per a la competició Albayzin-RTVE 2020 Speech-to-Text Challenge. El sistema primari (p-streaming_1500ms_nlt) és un sistema de RAP híbrid BLSTM-HMM amb descodificació en temps real en una passada amb una finestra de context d'1,5 segons i una combinació lineal de models de llenguatge (ML) d'n-grames, LSTM i Transformer. El model acústic s'ha entrenat amb vora 4000 hores de parla transcrita de diferents fonts, usant el transLectures-UPV toolkit (TLK) del grup MLLP i TensorFlow; mentre que els ML s'han entrenat amb SRILM (n-grames), CUED-RNNLM (LSTM) i Fairseq (Transformer), amb 102G paraules (tokens). Aquest sistema ha obtingut 11,6 % i 16,0 % de WER en els conjunts test-2018 i test-2020, respectivament. És un sistema amb capacitat de temps real, que pot desplegar-se en producció per a subtitulació automàtica de fluxos audiovisuals en directe, amb un retard teòric d'1,5 segons. A banda del sistema primari, s'han presentat tres sistemes contrastius. D'aquests, destaquem el sistema c2-streaming_600ms_t que, amb la mateixa configuració que el sistema primari, però amb una finestra de context més reduïda de 0,6 segons i un ML Transformer, ha obtingut 12,3 % i 16,9 % de WER, respectivament, sobre els mateixos conjunts, amb una latència empírica mesurada de 0,81+-0,09 segons (mitjana+-desv). És a dir, s'han obtingut latències punteres per a subtitulació automàtica en directe d'alta qualitat amb una degradació del WER petita, del 6 % relatiu. |
Garcés Díaz-Munío, Gonçal V; Silvestre-Cerdà, Joan Albert ; Jorge, Javier; Giménez, Adrià; Iranzo-Sánchez, Javier; Baquero-Arnal, Pau; Roselló, Nahuel; Pérez-González-de-Martos, Alejandro; Civera, Jorge; Sanchis, Albert; Juan, Alfons Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization Inproceedings Proc. Interspeech 2021, pp. 3695–3699, Brno (Czech Republic), 2021. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, speech corpus, speech data filtering, speech data verbatimization @inproceedings{Garcés2021, title = {Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization}, author = {Garcés Díaz-Munío, Gonçal V. and Silvestre-Cerdà, Joan Albert and Javier Jorge and Adrià Giménez and Javier Iranzo-Sánchez and Pau Baquero-Arnal and Nahuel Roselló and Alejandro Pérez-González-de-Martos and Jorge Civera and Albert Sanchis and Alfons Juan}, url = {https://www.mllp.upv.es/wp-content/uploads/2021/09/europarl-asr-presentation-extended.pdf https://www.youtube.com/watch?v=Tc0gNSDdnQg&list=PLlePn-Yanvnc_LRhgmmaNmH12Bwm6BRsZ https://paperswithcode.com/paper/europarl-asr-a-large-corpus-of-parliamentary https://github.com/mllpresearch/Europarl-ASR}, doi = {10.21437/Interspeech.2021-1905}, year = {2021}, date = {2021-01-01}, booktitle = {Proc. Interspeech 2021}, journal = {Proc. Interspeech 2021}, pages = {3695--3699}, address = {Brno (Czech Republic)}, abstract = {[EN] We introduce Europarl-ASR, a large speech and text corpus of parliamentary debates including 1300 hours of transcribed speeches and 70 million tokens of text in English extracted from European Parliament sessions. The training set is labelled with the Parliament’s non-fully-verbatim official transcripts, time-aligned. As verbatimness is critical for acoustic model training, we also provide automatically noise-filtered and automatically verbatimized transcripts of all speeches based on speech data filtering and verbatimization techniques. Additionally, 18 hours of transcribed speeches were manually verbatimized to build reliable speaker-dependent and speaker-independent development/test sets for streaming ASR benchmarking. The availability of manual non-verbatim and verbatim transcripts for dev/test speeches makes this corpus useful for the assessment of automatic filtering and verbatimization techniques. This paper describes the corpus and its creation, and provides off-line and streaming ASR baselines for both the speaker-dependent and speaker-independent tasks using the three training transcription sets. The corpus is publicly released under an open licence. [CA] "Europarl-ASR: Un extens corpus parlamentari de referència per a reconeixement de la parla i filtratge/literalització de transcripcions": Presentem Europarl-ASR, un extens corpus de veu i text de debats parlamentaris amb 1300 hores d'intervencions transcrites i 70 milions de paraules de text en anglés extrets de sessions del Parlament Europeu. Les transcripcions oficials del Parlament Europeu, no literals, s'han sincronitzat per a tot el conjunt d'entrenament. Com que l'entrenament de models acústics requereix transcripcions com més literals millor, també s'han inclòs transcripcions filtrades i transcripcions literalitzades de totes les intervencions, basades en tècniques de filtratge i literalització automàtics. A més, s'han inclòs 18 hores de transcripcions literals revisades manualment per definir dos conjunts de validació i avaluació de referència per a reconeixement automàtic de la parla en temps real, amb oradors coneguts i amb oradors desconeguts. Pel fet de disposar de transcripcions literals i no literals, aquest corpus és també ideal per a l'anàlisi de tècniques de filtratge i de literalització. En aquest article, es descriu la creació del corpus i es proporcionen mesures de referència de reconeixement automàtic de la parla en temps real i en diferit, amb oradors coneguts i amb oradors desconeguts, usant els tres conjunts de transcripcions d'entrenament. El corpus es fa públic amb una llicència oberta.}, keywords = {Automatic Speech Recognition, speech corpus, speech data filtering, speech data verbatimization}, pubstate = {published}, tppubtype = {inproceedings} } [EN] We introduce Europarl-ASR, a large speech and text corpus of parliamentary debates including 1300 hours of transcribed speeches and 70 million tokens of text in English extracted from European Parliament sessions. The training set is labelled with the Parliament’s non-fully-verbatim official transcripts, time-aligned. As verbatimness is critical for acoustic model training, we also provide automatically noise-filtered and automatically verbatimized transcripts of all speeches based on speech data filtering and verbatimization techniques. Additionally, 18 hours of transcribed speeches were manually verbatimized to build reliable speaker-dependent and speaker-independent development/test sets for streaming ASR benchmarking. The availability of manual non-verbatim and verbatim transcripts for dev/test speeches makes this corpus useful for the assessment of automatic filtering and verbatimization techniques. This paper describes the corpus and its creation, and provides off-line and streaming ASR baselines for both the speaker-dependent and speaker-independent tasks using the three training transcription sets. The corpus is publicly released under an open licence. [CA] "Europarl-ASR: Un extens corpus parlamentari de referència per a reconeixement de la parla i filtratge/literalització de transcripcions": Presentem Europarl-ASR, un extens corpus de veu i text de debats parlamentaris amb 1300 hores d'intervencions transcrites i 70 milions de paraules de text en anglés extrets de sessions del Parlament Europeu. Les transcripcions oficials del Parlament Europeu, no literals, s'han sincronitzat per a tot el conjunt d'entrenament. Com que l'entrenament de models acústics requereix transcripcions com més literals millor, també s'han inclòs transcripcions filtrades i transcripcions literalitzades de totes les intervencions, basades en tècniques de filtratge i literalització automàtics. A més, s'han inclòs 18 hores de transcripcions literals revisades manualment per definir dos conjunts de validació i avaluació de referència per a reconeixement automàtic de la parla en temps real, amb oradors coneguts i amb oradors desconeguts. Pel fet de disposar de transcripcions literals i no literals, aquest corpus és també ideal per a l'anàlisi de tècniques de filtratge i de literalització. En aquest article, es descriu la creació del corpus i es proporcionen mesures de referència de reconeixement automàtic de la parla en temps real i en diferit, amb oradors coneguts i amb oradors desconeguts, usant els tres conjunts de transcripcions d'entrenament. El corpus es fa públic amb una llicència oberta.
|
Iranzo-Sánchez, Javier; Jorge, Javier; Baquero-Arnal, Pau; Silvestre-Cerdà, Joan Albert ; Giménez, Adrià; Civera, Jorge; Sanchis, Albert; Juan, Alfons Streaming cascade-based speech translation leveraged by a direct segmentation model Journal Article Neural Networks, 142 , pp. 303–315, 2021. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Cascade System, Deep Neural Networks, Hybrid System, Machine Translation, Segmentation Model, Speech Translation, streaming @article{Iranzo-Sánchez2021, title = {Streaming cascade-based speech translation leveraged by a direct segmentation model}, author = {Javier Iranzo-Sánchez and Javier Jorge and Pau Baquero-Arnal and Silvestre-Cerdà, Joan Albert and Adrià Giménez and Jorge Civera and Albert Sanchis and Alfons Juan}, doi = {10.1016/j.neunet.2021.05.013}, year = {2021}, date = {2021-01-01}, journal = {Neural Networks}, volume = {142}, pages = {303--315}, abstract = {The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. Nowadays, state-of-the-art ST systems are populated with deep neural networks that are conceived to work in an offline setup in which the audio input to be translated is fully available in advance. However, a streaming setup defines a completely different picture, in which an unbounded audio input gradually becomes available and at the same time the translation needs to be generated under real-time constraints. In this work, we present a state-of-the-art streaming ST system in which neural-based models integrated in the ASR and MT components are carefully adapted in terms of their training and decoding procedures in order to run under a streaming setup. In addition, a direct segmentation model that adapts the continuous ASR output to the capacity of simultaneous MT systems trained at the sentence level is introduced to guarantee low latency while preserving the translation quality of the complete ST system. The resulting ST system is thoroughly evaluated on the real-life streaming Europarl-ST benchmark to gauge the trade-off between quality and latency for each component individually as well as for the complete ST system.}, keywords = {Automatic Speech Recognition, Cascade System, Deep Neural Networks, Hybrid System, Machine Translation, Segmentation Model, Speech Translation, streaming}, pubstate = {published}, tppubtype = {article} } The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. Nowadays, state-of-the-art ST systems are populated with deep neural networks that are conceived to work in an offline setup in which the audio input to be translated is fully available in advance. However, a streaming setup defines a completely different picture, in which an unbounded audio input gradually becomes available and at the same time the translation needs to be generated under real-time constraints. In this work, we present a state-of-the-art streaming ST system in which neural-based models integrated in the ASR and MT components are carefully adapted in terms of their training and decoding procedures in order to run under a streaming setup. In addition, a direct segmentation model that adapts the continuous ASR output to the capacity of simultaneous MT systems trained at the sentence level is introduced to guarantee low latency while preserving the translation quality of the complete ST system. The resulting ST system is thoroughly evaluated on the real-life streaming Europarl-ST benchmark to gauge the trade-off between quality and latency for each component individually as well as for the complete ST system. |
Pérez-González-de-Martos, Alejandro; Iranzo-Sánchez, Javier; Giménez Pastor, Adrià ; Jorge, Javier; Silvestre-Cerdà, Joan-Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons Towards simultaneous machine interpretation Inproceedings Proc. Interspeech 2021, pp. 2277–2281, Brno (Czech Republic), 2021. Abstract | Links | BibTeX | Tags: cross-lingual voice cloning, incremental text-to-speech, simultaneous machine interpretation, speech-to-speech translation @inproceedings{Pérez-González-de-Martos2021, title = {Towards simultaneous machine interpretation}, author = {Alejandro Pérez-González-de-Martos and Javier Iranzo-Sánchez and Giménez Pastor, Adrià and Javier Jorge and Joan-Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchis and Alfons Juan}, doi = {10.21437/Interspeech.2021-201}, year = {2021}, date = {2021-01-01}, booktitle = {Proc. Interspeech 2021}, journal = {Proc. Interspeech 2021}, pages = {2277--2281}, address = {Brno (Czech Republic)}, abstract = {Automatic speech-to-speech translation (S2S) is one of the most challenging speech and language processing tasks, especially when considering its application to real-time settings. Recent advances in streaming Automatic Speech Recognition (ASR), simultaneous Machine Translation (MT) and incremental neural Text-To-Speech (TTS) make it possible to develop real-time cascade S2S systems with greatly improved accuracy. On the way to simultaneous machine interpretation, a state-of-the-art cascade streaming S2S system is described and empirically assessed in the simultaneous interpretation of European Parliament debates. We pay particular attention to the TTS component, particularly in terms of speech naturalness under a variety of response-time settings, as well as in terms of speaker similarity for its cross-lingual voice cloning capabilities.}, keywords = {cross-lingual voice cloning, incremental text-to-speech, simultaneous machine interpretation, speech-to-speech translation}, pubstate = {published}, tppubtype = {inproceedings} } Automatic speech-to-speech translation (S2S) is one of the most challenging speech and language processing tasks, especially when considering its application to real-time settings. Recent advances in streaming Automatic Speech Recognition (ASR), simultaneous Machine Translation (MT) and incremental neural Text-To-Speech (TTS) make it possible to develop real-time cascade S2S systems with greatly improved accuracy. On the way to simultaneous machine interpretation, a state-of-the-art cascade streaming S2S system is described and empirically assessed in the simultaneous interpretation of European Parliament debates. We pay particular attention to the TTS component, particularly in terms of speech naturalness under a variety of response-time settings, as well as in terms of speaker similarity for its cross-lingual voice cloning capabilities. |
2020 |
Iranzo-Sánchez, Javier; Giménez Pastor, Adrià ; Silvestre-Cerdà, Joan Albert; Baquero-Arnal, Pau; Saiz, Jorge Civera; Juan, Alfons Direct Segmentation Models for Streaming Speech Translation Inproceedings Proc. of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), pp. 2599–2611, 2020. Abstract | Links | BibTeX | Tags: Segmentation, Speech Translation, streaming @inproceedings{Iranzo-Sánchez2020, title = {Direct Segmentation Models for Streaming Speech Translation}, author = {Javier Iranzo-Sánchez and Giménez Pastor, Adrià and Joan Albert Silvestre-Cerdà and Pau Baquero-Arnal and Jorge Civera Saiz and Alfons Juan}, url = {http://dx.doi.org/10.18653/v1/2020.emnlp-main.206}, year = {2020}, date = {2020-01-01}, booktitle = {Proc. of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)}, pages = {2599--2611}, abstract = {The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into, hopefully, semantically self-contained chunks to be fed into the MT system. This is especially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and thorough experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work.}, keywords = {Segmentation, Speech Translation, streaming}, pubstate = {published}, tppubtype = {inproceedings} } The cascade approach to Speech Translation (ST) is based on a pipeline that concatenates an Automatic Speech Recognition (ASR) system followed by a Machine Translation (MT) system. These systems are usually connected by a segmenter that splits the ASR output into, hopefully, semantically self-contained chunks to be fed into the MT system. This is especially challenging in the case of streaming ST, where latency requirements must also be taken into account. This work proposes novel segmentation models for streaming ST that incorporate not only textual, but also acoustic information to decide when the ASR output is split into a chunk. An extensive and thorough experimental setup is carried out on the Europarl-ST dataset to prove the contribution of acoustic information to the performance of the segmentation model in terms of BLEU score in a streaming ST scenario. Finally, comparative results with previous work also show the superiority of the segmentation models proposed in this work. |
Baquero-Arnal, Pau ; Jorge, Javier ; Giménez, Adrià ; Silvestre-Cerdà, Joan Albert ; Iranzo-Sánchez, Javier ; Sanchis, Albert ; Civera, Jorge ; Juan, Alfons Improved Hybrid Streaming ASR with Transformer Language Models Inproceedings Proc. of 21st Annual Conf. of the Intl. Speech Communication Association (InterSpeech 2020), pp. 2127–2131, Shanghai (China), 2020. Abstract | Links | BibTeX | Tags: hybrid ASR, language models, streaming, Transformer @inproceedings{Baquero-Arnal2020, title = {Improved Hybrid Streaming ASR with Transformer Language Models}, author = {Baquero-Arnal, Pau and Jorge, Javier and Giménez, Adrià and Silvestre-Cerdà, Joan Albert and Iranzo-Sánchez, Javier and Sanchis, Albert and Civera, Jorge and Juan, Alfons}, url = {http://dx.doi.org/10.21437/Interspeech.2020-2770}, year = {2020}, date = {2020-01-01}, booktitle = {Proc. of 21st Annual Conf. of the Intl. Speech Communication Association (InterSpeech 2020)}, pages = {2127--2131}, address = {Shanghai (China)}, abstract = {Streaming ASR is gaining momentum due to its wide applicability, though it is still unclear how best to come close to the accuracy of state-of-the-art off-line ASR systems when the output must come within a short delay after the incoming audio stream. Following our previous work on streaming one-pass decoding with hybrid ASR systems and LSTM language models, in this work we report further improvements by replacing LSTMs with Transformer models. First, two key ideas are discussed so as to run these models fast during inference. Then, empirical results on LibriSpeech and TED-LIUM are provided showing that Transformer language models lead to improved recognition rates on both tasks. ASR systems obtained in this work can be seamlessly transfered to a streaming setup with minimal quality losses. Indeed, to the best of our knowledge, no better results have been reported on these tasks when assessed under a streaming setup.}, keywords = {hybrid ASR, language models, streaming, Transformer}, pubstate = {published}, tppubtype = {inproceedings} } Streaming ASR is gaining momentum due to its wide applicability, though it is still unclear how best to come close to the accuracy of state-of-the-art off-line ASR systems when the output must come within a short delay after the incoming audio stream. Following our previous work on streaming one-pass decoding with hybrid ASR systems and LSTM language models, in this work we report further improvements by replacing LSTMs with Transformer models. First, two key ideas are discussed so as to run these models fast during inference. Then, empirical results on LibriSpeech and TED-LIUM are provided showing that Transformer language models lead to improved recognition rates on both tasks. ASR systems obtained in this work can be seamlessly transfered to a streaming setup with minimal quality losses. Indeed, to the best of our knowledge, no better results have been reported on these tasks when assessed under a streaming setup. |
Iranzo-Sánchez, Javier; Silvestre-Cerdà, Joan Albert; Jorge, Javier; Roselló, Nahuel; Giménez, Adrià; Sanchis, Albert; Civera, Jorge; Juan, Alfons Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates Inproceedings Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020), pp. 8229–8233, Barcelona (Spain), 2020. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Machine Translation, Multilingual Corpus, Speech Translation, Spoken Language Translation @inproceedings{Iranzo2020, title = {Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates}, author = {Javier Iranzo-Sánchez and Joan Albert Silvestre-Cerdà and Javier Jorge and Nahuel Roselló and Adrià Giménez and Albert Sanchis and Jorge Civera and Alfons Juan}, url = {https://arxiv.org/abs/1911.03167 https://paperswithcode.com/paper/europarl-st-a-multilingual-corpus-for-speech https://www.mllp.upv.es/europarl-st/}, doi = {10.1109/ICASSP40776.2020.9054626}, year = {2020}, date = {2020-01-01}, booktitle = {Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020)}, pages = {8229--8233}, address = {Barcelona (Spain)}, abstract = {Current research into spoken language translation (SLT), or speech-to-text translation, is often hampered by the lack of specific data resources for this task, as currently available SLT datasets are restricted to a limited set of language pairs. In this paper we present Europarl-ST, a novel multilingual SLT corpus containing paired audio-text samples for SLT from and into 6 European languages, for a total of 30 different translation directions. This corpus has been compiled using the de-bates held in the European Parliament in the period between2008 and 2012. This paper describes the corpus creation process and presents a series of automatic speech recognition,machine translation and spoken language translation experiments that highlight the potential of this new resource. The corpus is released under a Creative Commons license and is freely accessible and downloadable.}, keywords = {Automatic Speech Recognition, Machine Translation, Multilingual Corpus, Speech Translation, Spoken Language Translation}, pubstate = {published}, tppubtype = {inproceedings} } Current research into spoken language translation (SLT), or speech-to-text translation, is often hampered by the lack of specific data resources for this task, as currently available SLT datasets are restricted to a limited set of language pairs. In this paper we present Europarl-ST, a novel multilingual SLT corpus containing paired audio-text samples for SLT from and into 6 European languages, for a total of 30 different translation directions. This corpus has been compiled using the de-bates held in the European Parliament in the period between2008 and 2012. This paper describes the corpus creation process and presents a series of automatic speech recognition,machine translation and spoken language translation experiments that highlight the potential of this new resource. The corpus is released under a Creative Commons license and is freely accessible and downloadable. |
Jorge, Javier; Giménez, Adrià; Iranzo-Sánchez, Javier; Silvestre-Cerdà, Joan Albert; Civera, Jorge; Sanchis, Albert; Juan, Alfons LSTM-Based One-Pass Decoder for Low-Latency Streaming Inproceedings Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020), pp. 7814–7818, Barcelona (Spain), 2020. Abstract | Links | BibTeX | Tags: acoustic modeling, Automatic Speech Recognition, decoding, Language Modeling, streaming @inproceedings{Jorge2020, title = {LSTM-Based One-Pass Decoder for Low-Latency Streaming}, author = {Javier Jorge and Adrià Giménez and Javier Iranzo-Sánchez and Joan Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchis and Alfons Juan}, url = {https://www.mllp.upv.es/wp-content/uploads/2020/01/jorge2020_preprint.pdf https://doi.org/10.1109/ICASSP40776.2020.9054267}, year = {2020}, date = {2020-01-01}, booktitle = {Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020)}, pages = {7814--7818}, address = {Barcelona (Spain)}, abstract = {Current state-of-the-art models based on Long-Short Term Memory (LSTM) networks have been extensively used in ASR to improve performance. However, using LSTMs under a streaming setup is not straightforward due to real-time constraints. In this paper we present a novel streaming decoder that includes a bidirectional LSTM acoustic model as well as an unidirectional LSTM language model to perform the decoding efficiently while keeping the performance comparable to that of an off-line setup. We perform a one-pass decoding using a sliding window scheme for a bidirectional LSTM acoustic model and an LSTM language model. This has been implemented and assessed under a pure streaming setup, and deployed into our production systems. We report WER and latency figures for the well-known LibriSpeech and TED-LIUM tasks, obtaining competitive WER results with low-latency responses.}, keywords = {acoustic modeling, Automatic Speech Recognition, decoding, Language Modeling, streaming}, pubstate = {published}, tppubtype = {inproceedings} } Current state-of-the-art models based on Long-Short Term Memory (LSTM) networks have been extensively used in ASR to improve performance. However, using LSTMs under a streaming setup is not straightforward due to real-time constraints. In this paper we present a novel streaming decoder that includes a bidirectional LSTM acoustic model as well as an unidirectional LSTM language model to perform the decoding efficiently while keeping the performance comparable to that of an off-line setup. We perform a one-pass decoding using a sliding window scheme for a bidirectional LSTM acoustic model and an LSTM language model. This has been implemented and assessed under a pure streaming setup, and deployed into our production systems. We report WER and latency figures for the well-known LibriSpeech and TED-LIUM tasks, obtaining competitive WER results with low-latency responses. |
2019 |
Jorge, Javier; Giménez, Adrià; Iranzo-Sánchez, Javier; Civera, Jorge; Sanchis, Albert; Juan, Alfons Real-time One-pass Decoder for Speech Recognition Using LSTM Language Models Inproceedings Proc. of the 20th Annual Conf. of the ISCA (Interspeech 2019), pp. 3820–3824, Graz (Austria), 2019. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, LSTM language models, one-pass decoding, real-time @inproceedings{Jorge2019, title = {Real-time One-pass Decoder for Speech Recognition Using LSTM Language Models}, author = {Javier Jorge and Adrià Giménez and Javier Iranzo-Sánchez and Jorge Civera and Albert Sanchis and Alfons Juan}, url = {https://www.isca-speech.org/archive/interspeech_2019/jorge19_interspeech.html}, year = {2019}, date = {2019-01-01}, booktitle = {Proc. of the 20th Annual Conf. of the ISCA (Interspeech 2019)}, pages = {3820--3824}, address = {Graz (Austria)}, abstract = {Recurrent Neural Networks, in particular Long-Short Term Memory (LSTM) networks, are widely used in Automatic Speech Recognition for language modelling during decoding, usually as a mechanism for rescoring hypothesis. This paper proposes a new architecture to perform real-time one-pass decoding using LSTM language models. To make decoding efficient, the estimation of look-ahead scores was accelerated by precomputing static look-ahead tables. These static tables were precomputed from a pruned n-gram model, reducing drastically the computational cost during decoding. Additionally, the LSTM language model evaluation was efficiently performed using Variance Regularization along with a strategy of lazy evaluation. The proposed one-pass decoder architecture was evaluated on the well-known LibriSpeech and TED-LIUMv3 datasets. Results showed that the proposed algorithm obtains very competitive WERs with ∼0.6 RTFs. Finally, our one-pass decoder is compared with a decoupled two-pass decoder.}, keywords = {Automatic Speech Recognition, LSTM language models, one-pass decoding, real-time}, pubstate = {published}, tppubtype = {inproceedings} } Recurrent Neural Networks, in particular Long-Short Term Memory (LSTM) networks, are widely used in Automatic Speech Recognition for language modelling during decoding, usually as a mechanism for rescoring hypothesis. This paper proposes a new architecture to perform real-time one-pass decoding using LSTM language models. To make decoding efficient, the estimation of look-ahead scores was accelerated by precomputing static look-ahead tables. These static tables were precomputed from a pruned n-gram model, reducing drastically the computational cost during decoding. Additionally, the LSTM language model evaluation was efficiently performed using Variance Regularization along with a strategy of lazy evaluation. The proposed one-pass decoder architecture was evaluated on the well-known LibriSpeech and TED-LIUMv3 datasets. Results showed that the proposed algorithm obtains very competitive WERs with ∼0.6 RTFs. Finally, our one-pass decoder is compared with a decoupled two-pass decoder. |
2018 |
Del-Agua, Miguel Ángel ; Giménez, Adrià ; Sanchis, Alberto ; Civera, Jorge; Juan, Alfons Speaker-Adapted Confidence Measures for ASR using Deep Bidirectional Recurrent Neural Networks Journal Article IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26 (7), pp. 1194–1202, 2018. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Confidence estimation, Confidence measures, Deep bidirectional recurrent neural networks, Long short-term memory, Speaker adaptation @article{Del-Agua2018, title = {Speaker-Adapted Confidence Measures for ASR using Deep Bidirectional Recurrent Neural Networks}, author = {Del-Agua, Miguel Ángel AND Giménez, Adrià AND Sanchis, Alberto AND Civera,Jorge AND Juan, Alfons}, url = {http://www.mllp.upv.es/wp-content/uploads/2018/04/Del-Agua2018_authors_version.pdf https://doi.org/10.1109/TASLP.2018.2819900}, year = {2018}, date = {2018-01-01}, journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing}, volume = {26}, number = {7}, pages = {1194--1202}, abstract = {In the last years, Deep Bidirectional Recurrent Neural Networks (DBRNN) and DBRNN with Long Short-Term Memory cells (DBLSTM) have outperformed the most accurate classifiers for confidence estimation in automatic speech recognition. At the same time, we have recently shown that speaker adaptation of confidence measures using DBLSTM yields significant improvements over non-adapted confidence measures. In accordance with these two recent contributions to the state of the art in confidence estimation, this paper presents a comprehensive study of speaker-adapted confidence measures using DBRNN and DBLSTM models. Firstly, we present new empirical evidences of the superiority of RNN-based confidence classifiers evaluated over a large speech corpus consisting of the English LibriSpeech and the Spanish poliMedia tasks. Secondly, we show new results on speaker-adapted confidence measures considering a multi-task framework in which RNN-based confidence classifiers trained with LibriSpeech are adapted to speakers of the TED-LIUM corpus. These experiments confirm that speaker-adapted confidence measures outperform their non-adapted counterparts. Lastly, we describe an unsupervised adaptation method of the acoustic DBLSTM model based on confidence measures which results in better automatic speech recognition performance.}, keywords = {Automatic Speech Recognition, Confidence estimation, Confidence measures, Deep bidirectional recurrent neural networks, Long short-term memory, Speaker adaptation}, pubstate = {published}, tppubtype = {article} } In the last years, Deep Bidirectional Recurrent Neural Networks (DBRNN) and DBRNN with Long Short-Term Memory cells (DBLSTM) have outperformed the most accurate classifiers for confidence estimation in automatic speech recognition. At the same time, we have recently shown that speaker adaptation of confidence measures using DBLSTM yields significant improvements over non-adapted confidence measures. In accordance with these two recent contributions to the state of the art in confidence estimation, this paper presents a comprehensive study of speaker-adapted confidence measures using DBRNN and DBLSTM models. Firstly, we present new empirical evidences of the superiority of RNN-based confidence classifiers evaluated over a large speech corpus consisting of the English LibriSpeech and the Spanish poliMedia tasks. Secondly, we show new results on speaker-adapted confidence measures considering a multi-task framework in which RNN-based confidence classifiers trained with LibriSpeech are adapted to speakers of the TED-LIUM corpus. These experiments confirm that speaker-adapted confidence measures outperform their non-adapted counterparts. Lastly, we describe an unsupervised adaptation method of the acoustic DBLSTM model based on confidence measures which results in better automatic speech recognition performance. |
Jorge, Javier ; Martínez-Villaronga, Adrià ; Golik, Pavel ; Giménez, Adrià ; Silvestre-Cerdà, Joan Albert ; Doetsch, Patrick ; Císcar, Vicent Andreu ; Ney, Hermann ; Juan, Alfons ; Sanchis, Albert MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge Inproceedings Proc. of IberSPEECH 2018: 10th Jornadas en Tecnologías del Habla and 6th Iberian SLTech Workshop, pp. 257–261, Barcelona (Spain), 2018. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Iberspeech-RTVE-Challenge2018, IberSpeech2018, Speech-to-Text @inproceedings{Jorge2018, title = {MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge}, author = {Jorge, Javier and Martínez-Villaronga, Adrià and Golik, Pavel and Giménez, Adrià and Silvestre-Cerdà, Joan Albert and Doetsch, Patrick and Císcar, Vicent Andreu and Ney, Hermann and Juan, Alfons and Sanchis, Albert}, doi = {10.21437/IberSPEECH.2018-54}, year = {2018}, date = {2018-01-01}, booktitle = {Proc. of IberSPEECH 2018: 10th Jornadas en Tecnologías del Habla and 6th Iberian SLTech Workshop}, pages = {257--261}, address = {Barcelona (Spain)}, abstract = {This paper describes the Automatic Speech Recognition systems built by the MLLP research group of Universitat Politècnica de València and the HLTPR research group of RWTH Aachen for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge. We participated in both the closed and the open training conditions. The best system built for the closed conditions was a hybrid BLSTM-HMM ASR system using one-pass decoding with a combination of an RNN LM and show-adapted n-gram LMs. It was trained on a set of reliable speech data extracted from the train and dev1 sets using the MLLP’s transLectures-UPV toolkit (TLK) and TensorFlow. This system achieved 20.0% WER on the dev2 set. For the open conditions, we used approx. 3800 hours of out-of-domain training data from multiple sources and trained a one-pass hybrid BLSTM-HMM ASR system using the open-source tools RASR and RETURNN developed at RWTH Aachen. This system scored 15.6% WER on the dev2 set. The highlights of these systems include robust speech data filtering for acoustic model training and show-specific language modelling.}, keywords = {Automatic Speech Recognition, Iberspeech-RTVE-Challenge2018, IberSpeech2018, Speech-to-Text}, pubstate = {published}, tppubtype = {inproceedings} } This paper describes the Automatic Speech Recognition systems built by the MLLP research group of Universitat Politècnica de València and the HLTPR research group of RWTH Aachen for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge. We participated in both the closed and the open training conditions. The best system built for the closed conditions was a hybrid BLSTM-HMM ASR system using one-pass decoding with a combination of an RNN LM and show-adapted n-gram LMs. It was trained on a set of reliable speech data extracted from the train and dev1 sets using the MLLP’s transLectures-UPV toolkit (TLK) and TensorFlow. This system achieved 20.0% WER on the dev2 set. For the open conditions, we used approx. 3800 hours of out-of-domain training data from multiple sources and trained a one-pass hybrid BLSTM-HMM ASR system using the open-source tools RASR and RETURNN developed at RWTH Aachen. This system scored 15.6% WER on the dev2 set. The highlights of these systems include robust speech data filtering for acoustic model training and show-specific language modelling. |
2016 |
del-Agua, Miguel Ángel; Piqueras, Santiago; Giménez, Adrià; Sanchis, Alberto; Civera, Jorge; Juan, Alfons ASR Confidence Estimation with Speaker-Adapted Recurrent Neural Networks Inproceedings Proc. of the 17th Annual Conf. of the ISCA (Interspeech 2016), pp. 3464–3468, San Francisco (USA), 2016. Abstract | Links | BibTeX | Tags: BLSTM, Confidence measures, Recurrent Neural Networks, Speaker adaptation, Speech Recognition @inproceedings{del-Agua2016, title = {ASR Confidence Estimation with Speaker-Adapted Recurrent Neural Networks}, author = {Miguel Ángel del-Agua and Santiago Piqueras and Adrià Giménez and Alberto Sanchis and Jorge Civera and Alfons Juan}, doi = {10.21437/Interspeech.2016-1142}, year = {2016}, date = {2016-09-08}, booktitle = {Proc. of the 17th Annual Conf. of the ISCA (Interspeech 2016)}, pages = {3464--3468}, address = {San Francisco (USA)}, abstract = {Confidence estimation for automatic speech recognition has been very recently improved by using Recurrent Neural Networks (RNNs), and also by speaker adaptation (on the basis of Conditional Random Fields). In this work, we explore how to obtain further improvements by combining RNNs and speaker adaptation. In particular, we explore different speaker-dependent and -independent data representations for Bidirectional Long Short Term Memory RNNs of various topologies. Empirical tests are reported on the LibriSpeech dataset, showing that the best results are achieved by the proposed combination of RNNs and speaker adaptation.}, keywords = {BLSTM, Confidence measures, Recurrent Neural Networks, Speaker adaptation, Speech Recognition}, pubstate = {published}, tppubtype = {inproceedings} } Confidence estimation for automatic speech recognition has been very recently improved by using Recurrent Neural Networks (RNNs), and also by speaker adaptation (on the basis of Conditional Random Fields). In this work, we explore how to obtain further improvements by combining RNNs and speaker adaptation. In particular, we explore different speaker-dependent and -independent data representations for Bidirectional Long Short Term Memory RNNs of various topologies. Empirical tests are reported on the LibriSpeech dataset, showing that the best results are achieved by the proposed combination of RNNs and speaker adaptation. |
del-Agua, Miguel Ángel; Martínez-Villaronga, Adrià; Giménez, Adrià; Sanchis, Alberto; Civera, Jorge; Juan, Alfons The MLLP system for the 4th CHiME Challenge Inproceedings Proc. of the 4th Intl. Workshop on Speech Processing in Everyday Environments (CHiME 2016), pp. 57–59, San Francisco (USA), 2016. Abstract | Links | BibTeX | Tags: @inproceedings{del-Aguadel-Agua2016, title = {The MLLP system for the 4th CHiME Challenge}, author = {Miguel Ángel del-Agua and Adrià Martínez-Villaronga and Adrià Giménez and Alberto Sanchis and Jorge Civera and Alfons Juan}, url = {http://www.mllp.upv.es/wp-content/uploads/2017/11/DelAgua2016-The_MLLP_system_for_the_4th_CHiME_Challenge.pdf http://hdl.handle.net/10251/177497 http://spandh.dcs.shef.ac.uk/chime_workshop/chime2016/chime2016proceedings.pdf}, year = {2016}, date = {2016-01-01}, booktitle = {Proc. of the 4th Intl. Workshop on Speech Processing in Everyday Environments (CHiME 2016)}, pages = {57--59}, address = {San Francisco (USA)}, abstract = {The MLLP's CHiME-4 system is presented in this paper. It has been built using the transLectures-UPV toolkit (TLK), developed by the MLLP research group, which makes use of state-of-the-art speech techniques. Our best system built for the CHiME-4 challenge consists on the combination of different sub-systems in order to deal with the variety of acoustic conditions. Each sub-system in turn, follows a hybrid approach with different acoustic models, such as Deep Neural Networks or BLSTM Networks.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } The MLLP's CHiME-4 system is presented in this paper. It has been built using the transLectures-UPV toolkit (TLK), developed by the MLLP research group, which makes use of state-of-the-art speech techniques. Our best system built for the CHiME-4 challenge consists on the combination of different sub-systems in order to deal with the variety of acoustic conditions. Each sub-system in turn, follows a hybrid approach with different acoustic models, such as Deep Neural Networks or BLSTM Networks. |
2015 |
del-Agua, Miguel Ángel; Martínez-Villaronga, Adrià; Piqueras, Santiago; Giménez, Adrià; Sanchis, Alberto; Civera, Jorge; Juan, Alfons The MLLP ASR Systems for IWSLT 2015 Inproceedings Proc. of 12th Intl. Workshop on Spoken Language Translation (IWSLT 2015), pp. 39–44, Da Nang (Vietnam), 2015. Abstract | Links | BibTeX | Tags: @inproceedings{delAgua15, title = {The MLLP ASR Systems for IWSLT 2015}, author = {Miguel Ángel del-Agua and Adrià Martínez-Villaronga and Santiago Piqueras and Adrià Giménez and Alberto Sanchis and Jorge Civera and Alfons Juan}, url = {https://aclanthology.org/2015.iwslt-evaluation.5/}, year = {2015}, date = {2015-12-03}, booktitle = {Proc. of 12th Intl. Workshop on Spoken Language Translation (IWSLT 2015)}, pages = {39--44}, address = {Da Nang (Vietnam)}, abstract = {This paper describes the Machine Learning and Language Processing (MLLP) ASR systems for the 2015 IWSLT evaluation campaing. The English system is based on the combination of five different subsystems which consist of two types of Neural Networks architectures (Deep feed-forward and Convolutional), two types of activation functions (sigmoid and rectified linear) and two types of input features (fMLLR and FBANK). All subsystems perform a speaker adaptation step based on confidence measures, the output of which is then combined with ROVER. This system achieves a Word Error Rate (WER) of 13.3% on the official IWSLT 2015 English test set.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } This paper describes the Machine Learning and Language Processing (MLLP) ASR systems for the 2015 IWSLT evaluation campaing. The English system is based on the combination of five different subsystems which consist of two types of Neural Networks architectures (Deep feed-forward and Convolutional), two types of activation functions (sigmoid and rectified linear) and two types of input features (fMLLR and FBANK). All subsystems perform a speaker adaptation step based on confidence measures, the output of which is then combined with ROVER. This system achieves a Word Error Rate (WER) of 13.3% on the official IWSLT 2015 English test set. |
Khoury, Ihab; Giménez, Adrià; Juan, Alfons; Andrés-Ferrer, Jesús Window Repositioning for Printed Arabic Recognition Journal Article Pattern Recognition Letters, 51 , pp. 86–93, 2015, ISSN: 0167-8655. Abstract | Links | BibTeX | Tags: Bernoulli HMMs, Printed Arabic Recognition, Repositioning, Sliding window @article{Kho14, title = {Window Repositioning for Printed Arabic Recognition}, author = {Ihab Khoury and Adrià Giménez and Alfons Juan and Jesús Andrés-Ferrer}, url = {http://dx.doi.org/10.1016/j.patrec.2014.08.009}, issn = {0167-8655}, year = {2015}, date = {2015-01-01}, journal = {Pattern Recognition Letters}, volume = {51}, pages = {86--93}, abstract = {Bernoulli HMMs are conventional HMMs in which the emission probabilities are modeled with Bernoulli mixtures. They have recently been applied, with good results, in off-line text recognition in many languages, in particular, Arabic. A key idea that has proven to be very effective in this application of Bernoulli HMMs is the use of a sliding window of adequate width for feature extraction. This idea has allowed us to obtain very competitive results in the recognition of both Arabic handwriting and printed text. Indeed, a system based on it ranked first at the ICDAR 2011 Arabic recognition competition on the Arabic Printed Text Image (APTI) database. More recently, this idea has been refined by using repositioning techniques for extracted windows, leading to further improvements in Arabic handwriting recognition. In the case of printed text, this refinement led to an improved system which ranked second at the ICDAR 2013 second competition on APTI, only at a marginal distance from the best system. In this work, we describe the development of this improved system. Following evaluation protocols similar to those of the competitions on APTI, exhaustive experiments are detailed from which state-of-the-art results are obtained.}, keywords = {Bernoulli HMMs, Printed Arabic Recognition, Repositioning, Sliding window}, pubstate = {published}, tppubtype = {article} } Bernoulli HMMs are conventional HMMs in which the emission probabilities are modeled with Bernoulli mixtures. They have recently been applied, with good results, in off-line text recognition in many languages, in particular, Arabic. A key idea that has proven to be very effective in this application of Bernoulli HMMs is the use of a sliding window of adequate width for feature extraction. This idea has allowed us to obtain very competitive results in the recognition of both Arabic handwriting and printed text. Indeed, a system based on it ranked first at the ICDAR 2011 Arabic recognition competition on the Arabic Printed Text Image (APTI) database. More recently, this idea has been refined by using repositioning techniques for extracted windows, leading to further improvements in Arabic handwriting recognition. In the case of printed text, this refinement led to an improved system which ranked second at the ICDAR 2013 second competition on APTI, only at a marginal distance from the best system. In this work, we describe the development of this improved system. Following evaluation protocols similar to those of the competitions on APTI, exhaustive experiments are detailed from which state-of-the-art results are obtained. |
2014 |
Giménez Pastor, Adrià Bernoulli HMMs for Handwritten Text Recognition PhD Thesis Universitat Politècnica de València , 2014, (Advisors: Alfons Juan Ciscar and Jesús Andrés Ferrer). @phdthesis{Pastor2014, title = {Bernoulli HMMs for Handwritten Text Recognition}, author = {Giménez Pastor, Adrià}, url = {http://hdl.handle.net/10251/37978}, year = {2014}, date = {2014-05-22}, school = {Universitat Politècnica de València }, note = {Advisors: Alfons Juan Ciscar and Jesús Andrés Ferrer}, keywords = {}, pubstate = {published}, tppubtype = {phdthesis} } |
Wuebker, Joern; Ney, Hermann; Martínez-Villaronga, Adrià; Giménez, Adrià; Juan, Alfons; Servan, Christophe; Dymetman, Marc; Mirkin, Shachar Comparison of Data Selection Techniques for the Translation of Video Lectures Inproceedings Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014), pp. 193–207, Vancouver (Canada), 2014. @inproceedings{WueMarSer14, title = {Comparison of Data Selection Techniques for the Translation of Video Lectures}, author = {Joern Wuebker and Hermann Ney and Adrià Martínez-Villaronga and Adrià Giménez and Alfons Juan and Christophe Servan and Marc Dymetman and Shachar Mirkin}, url = {https://aclanthology.org/2014.amta-researchers.15/}, year = {2014}, date = {2014-01-01}, booktitle = {Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014)}, pages = {193--207}, address = {Vancouver (Canada)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Serrano, Nicolás; Giménez, Adrià; Civera, Jorge; Sanchis, Alberto; Juan, Alfons Interactive Handwriting Recognition with Limited User effort Journal Article Intl. Journal on Document Analysis and Recognition (IJDAR), 17 , pp. 47–59, 2014. @article{Serrano14a, title = {Interactive Handwriting Recognition with Limited User effort}, author = {Nicolás Serrano and Adrià Giménez and Jorge Civera and Alberto Sanchis and Alfons Juan}, url = {http://dx.doi.org/10.1007/s10032-013-0204-5}, year = {2014}, date = {2014-01-01}, journal = {Intl. Journal on Document Analysis and Recognition (IJDAR)}, volume = {17}, pages = {47--59}, keywords = {}, pubstate = {published}, tppubtype = {article} } |
Giménez, Adrià; Andrés-Ferrer, Jesús; Juan, Alfons Discriminative Bernoulli HMMs for isolated handwritten word recognition Journal Article Pattern Recognition Letters, 35 (0), pp. 157–168, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). @article{Giménez2014157, title = {Discriminative Bernoulli HMMs for isolated handwritten word recognition}, author = {Adrià Giménez and Jesús Andrés-Ferrer and Alfons Juan}, url = {http://dx.doi.org/10.1016/j.patrec.2013.05.016}, issn = {0167-8655}, year = {2014}, date = {2014-01-01}, journal = {Pattern Recognition Letters}, volume = {35}, number = {0}, pages = {157--168}, note = {Frontiers in Handwriting Processing}, keywords = {RIMES}, pubstate = {published}, tppubtype = {article} } |
Giménez, Adrià; Khoury, Ihab; Andrés-Ferrer, Jesús; Juan, Alfons Handwriting word recognition using windowed Bernoulli HMMs Journal Article Pattern Recognition Letters, 35 (0), pp. 149–156, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). Links | BibTeX | Tags: Sliding window @article{Giménez2014149, title = {Handwriting word recognition using windowed Bernoulli HMMs}, author = {Adrià Giménez and Ihab Khoury and Jesús Andrés-Ferrer and Alfons Juan}, url = {http://dx.doi.org/10.1016/j.patrec.2012.09.002 http://hdl.handle.net/10251/37326}, issn = {0167-8655}, year = {2014}, date = {2014-01-01}, journal = {Pattern Recognition Letters}, volume = {35}, number = {0}, pages = {149--156}, note = {Frontiers in Handwriting Processing}, keywords = {Sliding window}, pubstate = {published}, tppubtype = {article} } |
Piqueras, S; del-Agua, M A; Giménez, A; Civera, J; Juan, A Statistical text-to-speech synthesis of Spanish subtitles Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. @inproceedings{PiqAgu14, title = {Statistical text-to-speech synthesis of Spanish subtitles}, author = {S. Piqueras and M. A. del-Agua and A. Giménez and J. Civera and A. Juan}, url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/paper3.pdf http://link.springer.com/chapter/10.1007%2F978-3-319-13623-3_5}, year = {2014}, date = {2014-01-01}, booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)}, address = {Las Palmas de Gran Canaria (Spain)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
del-Agua, M A; Giménez, A; Serrano, N; Andrés-Ferrer, J; Civera, J; Sanchis, A; Juan, A The transLectures-UPV toolkit Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. @inproceedings{AguGim14, title = {The transLectures-UPV toolkit}, author = {M. A. del-Agua and A. Giménez and N. Serrano and J. Andrés-Ferrer and J. Civera and A. Sanchis and A. Juan}, url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/IberSpeech2014-TLK-camready1.pdf}, year = {2014}, date = {2014-01-01}, booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)}, address = {Las Palmas de Gran Canaria (Spain)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
2013 |
Alkhoury, Ihab; Giménez, Adrià; Juan, Alfons; Andrés-Ferrer, Jesús Arabic Printed Word Recognition Using Windowed Bernoulli HMMs Inproceedings Proc. of the 17th Intl. Conf. on Image, Analysis and Processings (ICIAP 2013), pp. 330 – 339, Naples (Italy), 2013. @inproceedings{khoury13a, title = {Arabic Printed Word Recognition Using Windowed Bernoulli HMMs}, author = {Ihab Alkhoury and Adrià Giménez and Alfons Juan and Jesús Andrés-Ferrer}, url = {http://dx.doi.org/10.1007/978-3-642-41181-6_34}, year = {2013}, date = {2013-01-01}, booktitle = {Proc. of the 17th Intl. Conf. on Image, Analysis and Processings (ICIAP 2013)}, pages = {330 -- 339}, address = {Naples (Italy)}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } |
Khoury, Ihab ; Giménez, Adrià ; Andrés-Ferrer, Jesús ; Juan, Alfons ; Sánchez, Joan Andreu The UPV Handwriting Recognition and Translation System for OpenHaRT 2013 Inproceedings Proc. of the NIST Open Handwriting Recognition and Translation Evaluation Workshop (OpenHaRT 2013), Washington DC (USA), 2013. Links | BibTeX | Tags: Arabic HTR, Bernoulli HMM, NIST OpenHaRT, Repositioning, Sliding window @inproceedings{Khoury2013, title = {The UPV Handwriting Recognition and Translation System for OpenHaRT 2013}, author = {Khoury, Ihab and Giménez, Adrià and Andrés-Ferrer, Jesús and Juan, Alfons and Sánchez, Joan Andreu}, url = {http://www.nist.gov/itl/iad/mig/upload/OpenHaRT2013_SysDesc_UPV.pdf}, year = {2013}, date = {2013-01-01}, booktitle = {Proc. of the NIST Open Handwriting Recognition and Translation Evaluation Workshop (OpenHaRT 2013)}, address = {Washington DC (USA)}, keywords = {Arabic HTR, Bernoulli HMM, NIST OpenHaRT, Repositioning, Sliding window}, pubstate = {published}, tppubtype = {inproceedings} } |
Publications
2024 |
Segmentation-Free Streaming Machine Translation Journal Article Forthcoming Transactions of the Association for Computational Linguistics, 12 , Forthcoming, (also accepted for presentation at ACL 2024). |
2022 |
Doblaje automático de vídeo-charlas educativas en UPV[Media] Inproceedings Proc. of VIII Congrés d'Innovació Educativa i Docència en Xarxa (IN-RED 2022), pp. 557–570, València (Spain), 2022. |
MLLP-VRAIN UPV systems for the IWSLT 2022 Simultaneous Speech Translation and Speech-to-Speech Translation tasks Inproceedings Proc. of 19th Intl. Workshop on Spoken Language Translation (IWSLT 2022), pp. 255–264, Dublin (Ireland), 2022. |
MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge: Extension Journal Article Applied Sciences, 12 (2), pp. 804, 2022. |
2021 |
Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models Journal Article IEEE/ACM Transactions on Audio, Speech, and Language Processing, 30 , pp. 148–161, 2021. |
Towards cross-lingual voice cloning in higher education Journal Article Engineering Applications of Artificial Intelligence, 105 , pp. 104413, 2021. |
MLLP-VRAIN Spanish ASR Systems for the Albayzin-RTVE 2020 Speech-To-Text Challenge Inproceedings Proc. of IberSPEECH 2021, pp. 118–122, Valladolid (Spain), 2021. |
Europarl-ASR: A Large Corpus of Parliamentary Debates for Streaming ASR Benchmarking and Speech Data Filtering/Verbatimization Inproceedings Proc. Interspeech 2021, pp. 3695–3699, Brno (Czech Republic), 2021. |
Streaming cascade-based speech translation leveraged by a direct segmentation model Journal Article Neural Networks, 142 , pp. 303–315, 2021. |
Towards simultaneous machine interpretation Inproceedings Proc. Interspeech 2021, pp. 2277–2281, Brno (Czech Republic), 2021. |
2020 |
Direct Segmentation Models for Streaming Speech Translation Inproceedings Proc. of 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), pp. 2599–2611, 2020. |
Improved Hybrid Streaming ASR with Transformer Language Models Inproceedings Proc. of 21st Annual Conf. of the Intl. Speech Communication Association (InterSpeech 2020), pp. 2127–2131, Shanghai (China), 2020. |
Europarl-ST: A Multilingual Corpus for Speech Translation of Parliamentary Debates Inproceedings Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020), pp. 8229–8233, Barcelona (Spain), 2020. |
LSTM-Based One-Pass Decoder for Low-Latency Streaming Inproceedings Proc. of 45th Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP 2020), pp. 7814–7818, Barcelona (Spain), 2020. |
2019 |
Real-time One-pass Decoder for Speech Recognition Using LSTM Language Models Inproceedings Proc. of the 20th Annual Conf. of the ISCA (Interspeech 2019), pp. 3820–3824, Graz (Austria), 2019. |
2018 |
Speaker-Adapted Confidence Measures for ASR using Deep Bidirectional Recurrent Neural Networks Journal Article IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26 (7), pp. 1194–1202, 2018. |
MLLP-UPV and RWTH Aachen Spanish ASR Systems for the IberSpeech-RTVE 2018 Speech-to-Text Transcription Challenge Inproceedings Proc. of IberSPEECH 2018: 10th Jornadas en Tecnologías del Habla and 6th Iberian SLTech Workshop, pp. 257–261, Barcelona (Spain), 2018. |
2016 |
ASR Confidence Estimation with Speaker-Adapted Recurrent Neural Networks Inproceedings Proc. of the 17th Annual Conf. of the ISCA (Interspeech 2016), pp. 3464–3468, San Francisco (USA), 2016. |
The MLLP system for the 4th CHiME Challenge Inproceedings Proc. of the 4th Intl. Workshop on Speech Processing in Everyday Environments (CHiME 2016), pp. 57–59, San Francisco (USA), 2016. |
2015 |
The MLLP ASR Systems for IWSLT 2015 Inproceedings Proc. of 12th Intl. Workshop on Spoken Language Translation (IWSLT 2015), pp. 39–44, Da Nang (Vietnam), 2015. |
Window Repositioning for Printed Arabic Recognition Journal Article Pattern Recognition Letters, 51 , pp. 86–93, 2015, ISSN: 0167-8655. |
2014 |
Bernoulli HMMs for Handwritten Text Recognition PhD Thesis Universitat Politècnica de València , 2014, (Advisors: Alfons Juan Ciscar and Jesús Andrés Ferrer). |
Comparison of Data Selection Techniques for the Translation of Video Lectures Inproceedings Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014), pp. 193–207, Vancouver (Canada), 2014. |
Interactive Handwriting Recognition with Limited User effort Journal Article Intl. Journal on Document Analysis and Recognition (IJDAR), 17 , pp. 47–59, 2014. |
Discriminative Bernoulli HMMs for isolated handwritten word recognition Journal Article Pattern Recognition Letters, 35 (0), pp. 157–168, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). |
Handwriting word recognition using windowed Bernoulli HMMs Journal Article Pattern Recognition Letters, 35 (0), pp. 149–156, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). |
Statistical text-to-speech synthesis of Spanish subtitles Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. |
The transLectures-UPV toolkit Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. |
2013 |
Arabic Printed Word Recognition Using Windowed Bernoulli HMMs Inproceedings Proc. of the 17th Intl. Conf. on Image, Analysis and Processings (ICIAP 2013), pp. 330 – 339, Naples (Italy), 2013. |
The UPV Handwriting Recognition and Translation System for OpenHaRT 2013 Inproceedings Proc. of the NIST Open Handwriting Recognition and Translation Evaluation Workshop (OpenHaRT 2013), Washington DC (USA), 2013. |