Publications

@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{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}
}

@article{Miró2018,
title = {Multilingual videos for MOOCs and OER},
author = {Valor Miró, Juan Daniel and Pau Baquero-Arnal and Jorge Civera and Carlos Turró and Alfons Juan},
url = {https://www.mllp.upv.es/wp-content/uploads/2019/11/JETS2018MLLP.pdf
http://hdl.handle.net/10251/122577
https://www.jstor.org/stable/26388375
https://www.j-ets.net/collection/published-issues/21_2},
year = {2018},
date = {2018-01-01},
journal = {Journal of Educational Technology & Society},
volume = {21},
number = {2},
pages = {1--12},
abstract = {Massive Open Online Courses (MOOCs) and Open Educational Resources (OER) are rapidly growing, but are not usually offered in multiple languages due to the lack of cost-effective solutions to translate the different objects comprising them and particularly videos. However, current state-of-the-art automatic speech recognition (ASR) and machine translation (MT) techniques have reached a level of maturity which opens the possibility of producing multilingual video subtitles of publishable quality at low cost. This work summarizes authors' experience in exploring this possibility in two real-life case studies: a MOOC platform and a large video lecture repository. Apart from describing the systems, tools and integration components employed for such purpose, a comprehensive evaluation of the results achieved is provided in terms of quality and efficiency. More precisely, it is shown that draft multilingual subtitles produced by domain-adapted ASR/MT systems reach a level of accuracy that make them worth post-editing, instead of generating them ex novo, saving approximately 25%–75% of the time. Finally, the results reported on user multilingual data consumption reflect that multilingual subtitles have had a very positive impact in our case studies boosting student enrolment, in the case of the MOOC platform, by 70% relative.},
keywords = {Machine Translation, MOOCs, multilingual, Speech Recognition, video lecture repositories},
pubstate = {published},
tppubtype = {article}
}

@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}
}

@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}
}