Publications

@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}
}

@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}
}

@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}
}

@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},
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}
}

@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}
}

@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://doi.org/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}
}

@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}
}

@inproceedings{Silvestre-Cerdà2016b,
title = {Different Contributions to Cost-Effective Transcription and Translation of Video Lectures},
author = {Joan Albert Silvestre-Cerdà and Alfons Juan and Jorge Civera},
url = {http://www.mllp.upv.es/wp-content/uploads/2016/11/poster.pdf
http://www.mllp.upv.es/wp-content/uploads/2016/11/paper.pdf
http://hdl.handle.net/10251/62194},
isbn = {978-3-319-49168-4 },
year = {2016},
date = {2016-11-24},
booktitle = {Proc. of IX Jornadas en Tecnología del Habla and V Iberian SLTech Workshop (IberSpeech 2016)},
pages = {313-319},
address = {Lisbon (Portugal)},
abstract = {In recent years, on-line multimedia repositories have experiencied
a strong growth that have made them consolidated as essential
knowledge assets, especially in the area of education, where large repositories
of video lectures have been built in order to complement or even
replace traditional teaching methods. However, most of these video lectures
are neither transcribed nor translated due to a lack of cost-effective
solutions to do so in a way that gives accurate enough results. Solutions
of this kind are clearly necessary in order to make these lectures accessible
to speakers of different languages and to people with hearing
disabilities, among many other benefits and applications.
For this reason, the main aim of this thesis is to develop a cost-effective
solution capable of transcribing and translating video lectures to a reasonable
degree of accuracy. More specifically, we address the integration
of state-of-the-art techniques in Automatic Speech Recognition and Machine
Translation into large video lecture repositories to generate highquality
multilingual video subtitles without human intervention and at
a reduced computational cost. Also, we explore the potential benefits of
the exploitation of the information that we know a priori about these
repositories, that is, lecture-specific knowledge such as speaker, topic
or slides, to create specialised, in-domain transcription and translation
systems by means of massive adaptation techniques.
The proposed solutions have been tested in real-life scenarios by carrying
out several objective and subjective evaluations, obtaining very
positive results. The main outcome derived from this multidisciplinary
thesis, The transLectures-UPV Platform, has been publicly released as an
open-source software, and, at the time of writing, it is serving automatic
transcriptions and translations for several thousands of video lectures in
many Spanish and European universities and institutions.},
keywords = {Automatic Speech Recognition, Automatic transcription and translation, Machine Translation, Video Lectures},
pubstate = {published},
tppubtype = {inproceedings}
}

@article{Valor201565,
title = {Efficiency and usability study of innovative computer-aided transcription strategies for video lecture repositories},
author = {Valor Miró, Juan Daniel and Joan Albert Silvestre-Cerdà and Jorge Civera and Carlos Turró and Alfons Juan},
url = {http://www.sciencedirect.com/science/article/pii/S0167639315001016
http://www.mllp.upv.es/wp-content/uploads/2016/03/paper1.pdf},
issn = {0167-6393},
year = {2015},
date = {2015-01-01},
journal = {Speech Communication},
volume = {74},
pages = {65--75},
abstract = {Abstract Video lectures are widely used in education to support and complement face-to-face lectures. However, the utility of these audiovisual assets could be further improved by adding subtitles that can be exploited to incorporate added-value functionalities such as searchability, accessibility, translatability, note-taking, and discovery of content-related videos, among others. Today, automatic subtitles are prone to error, and need to be reviewed and post-edited in order to ensure that what students see on-screen are of an acceptable quality. This work investigates different user interface design strategies for this post-editing task to discover the best way to incorporate automatic transcription technologies into large educational video repositories. Our three-phase study involved lecturers from the Universitat Politècnica de València (UPV) with videos available on the poliMedia video lecture repository, which is currently over 10,000 video objects. Simply by conventional post-editing automatic transcriptions users almost reduced to half the time that would require to generate the transcription from scratch. As expected, this study revealed that the time spent by lecturers reviewing automatic transcriptions correlated directly with the accuracy of said transcriptions. However, it is also shown that the average time required to perform each individual editing operation could be precisely derived and could be applied in the definition of a user model. In addition, the second phase of this study presents a transcription review strategy based on confidence measures (CM) and compares it to the conventional post-editing strategy. Finally, a third strategy resulting from the combination of that based on \\{CM\\} with massive adaptation techniques for automatic speech recognition (ASR), achieved to improve the transcription review efficiency in comparison with the two aforementioned strategies.},
keywords = {Automatic Speech Recognition, Computer-assisted transcription, Interface design strategies, Usability study, video lecture repositories},
pubstate = {published},
tppubtype = {article}
}

@inproceedings{Brouns2015,
title = {Supporting language diversity of European MOOCs with the EMMA platform},
author = {Francis Brouns and Serrano Martínez-Santos, Nicolás and Jorge Civera and Marco Kalz and Alfons Juan},
url = {http://www.emoocs2015.eu/node/55},
year = {2015},
date = {2015-01-01},
booktitle = {Proc. of the European MOOC Stakeholder Summit EMOOCs 2015},
pages = {157--165},
address = {Mons (Belgium)},
abstract = {This paper introduces the cross-language support of the EMMA MOOC platform. Based on a discussion of language diversity in Europe, we introduce the development and evaluation of automated translation of texts and subtitling of videos from Dutch into English. The development of an Automatic Speech Recognition (ASR) system and a Statistical Machine Translation (SMT) system is described. The resources employed and evaluation approach is introduced. Initial evaluation results are presented. Finally, we provide an outlook into future research and development.},
keywords = {Automatic Speech Recognition, EMMA, Statistical machine translation},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Silvestre-Cerdà2013,
title = {A System Architecture to Support Cost-Effective Transcription and Translation of Large Video Lecture Repositories},
author = {Joan Albert Silvestre-Cerdà and Alejandro Pérez and Manuel Jiménez and Carlos Turró and Alfons Juan and Jorge Civera},
url = {http://dx.doi.org/10.1109/SMC.2013.682},
year = {2013},
date = {2013-01-01},
booktitle = {Proc. of the IEEE Intl. Conf. on Systems, Man, and Cybernetics SMC 2013 },
pages = {3994-3999},
address = {Manchester (UK)},
abstract = {Online video lecture repositories are rapidly growing and becoming established as fundamental knowledge assets. However, most lectures are neither transcribed nor translated because of the lack of cost-effective solutions that can give accurate enough results. In this paper, we describe a system architecture that supports the cost-effective transcription and translation of large video lecture repositories. This architecture has been adopted in the EU project transLectures and is now being tested on a repository of more than 9000 video lectures at the Universitat Politecnica de Valencia. Following a brief description of this repository and of the transLectures project, we describe the proposed system architecture in detail. We also report empirical results on the quality of the transcriptions and translations currently being maintained and steadily improved.},
keywords = {Accessibility, Automatic Speech Recognition, Education, Intelligent Interaction, Language Technologies, Machine Translation, Massive Adaptation, Multilingualism, Opencast Matterhorn, Video Lectures},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Silvestre-Cerdà2012b,
title = {transLectures},
author = {Silvestre-Cerdà, Joan Albert and Del Agua, Miguel and Gonçal Garcés and Guillem Gascó and Adrià Giménez-Pastor and Adrià Martínez and Pérez González de Martos, Alejandro and Isaías Sánchez and Serrano Martínez-Santos, Nicolás and Rachel Spencer and Valor Miró, Juan Daniel and Jesús Andrés-Ferrer and Jorge Civera and Alberto Sanchís and Alfons Juan},
url = {http://hdl.handle.net/10251/37290
http://lorien.die.upm.es/~lapiz/rtth/JORNADAS/VII/IberSPEECH2012_OnlineProceedings.pdf
https://web.archive.org/web/20130609073144/http://iberspeech2012.ii.uam.es/IberSPEECH2012_OnlineProceedings.pdf
http://www.mllp.upv.es/wp-content/uploads/2015/04/1209IberSpeech.pdf},
year = {2012},
date = {2012-11-22},
booktitle = {Proceedings (Online) of IberSPEECH 2012},
pages = {345--351},
address = {Madrid (Spain)},
abstract = {[EN] transLectures (Transcription and Translation of Video Lectures) is an EU STREP project in which advanced automatic speech recognition and machine translation techniques are being tested on large video lecture repositories. The project began in November 2011 and will run for three years. This paper will outline the project's main motivation and objectives, and give a brief description of the two main repositories being considered: VideoLectures.NET and poliMèdia. The first results obtained by the UPV group for the poliMedia repository will also be provided.

[CA] transLectures (Transcription and Translation of Video Lectures) és un projecte del 7PM de la Unió Europea en el qual s'estan posant a prova tècniques avançades de reconeixement automàtic de la parla i de traducció automàtica sobre grans repositoris digitals de vídeos docents. El projecte començà al novembre de 2011 i tindrà una duració de tres anys. En aquest article exposem la motivació i els objectius del projecte, i descrivim breument els dos repositoris principals sobre els quals es treballa: VideoLectures.NET i poliMèdia. També oferim els primers resultats obtinguts per l'equip de la UPV al repositori poliMèdia.},
keywords = {Accessibility, Automatic Speech Recognition, Education, Intelligent Interaction, Language Technologies, Machine Translation, Massive Adaptation, Multilingualism, Opencast Matterhorn, Video Lectures},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Turró2012,
title = {transLectures: Transcription and Translation of Video Lectures},
author = {Carlos Turró and Alfons Juan and Jorge Civera and Davor Orliĉ and Mitja Jermol},
url = {http://oro.open.ac.uk/id/eprint/33640
http://hdl.handle.net/10251/54166},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of Cambridge 2012: Innovation and Impact - Openly Collaborating to Enhance Education},
pages = {543-546},
address = {Cambridge (UK)},
abstract = {transLectures is a FP7 project aimed at developing innovative, cost-effective solutions to produce accurate transcriptions and translations in large repositories of video lectures. This paper describes user requirements, first integration steps and evaluation plans at transLectures case studies, VideoLectures.NET and poliMedia.},
keywords = {Automatic Speech Recognition, Statistical machine translation},
pubstate = {published},
tppubtype = {inproceedings}
}