Publications

@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}
}

@misc{mllpttp,
title = {MLLP Transcription and Translation Platform},
author = {Pérez González de Martos, Alejandro and Silvestre-Cerdà, Joan Albert and Valor Miró, Juan Daniel and Civera, Jorge and Juan, Alfons},
url = {http://hdl.handle.net/10251/65747
http://www.mllp.upv.es/wp-content/uploads/2015/09/ttp_platform_demo_ectel2015.pdf
http://ectel2015.httc.de/index.php?id=722},
year = {2015},
date = {2015-09-16},
booktitle = {Tenth European Conference On Technology Enhanced Learning (EC-TEL 2015)},
abstract = {This paper briefly presents the main features of MLLP’s Transcription and Translation Platform, which uses state-of-the-art automatic speech recognition and machine translation systems to generate multilingual subtitles of educational audiovisual and textual content. It has proven to reduce user effort up to 1/3 of the time needed to generate transcriptions and translations from scratch.},
note = {Short paper for demo presentation accepted at 10th European Conf. on Technology Enhanced Learning (EC-TEL 2015), Toledo (Spain), 2015.},
keywords = {Automatic Speech Recognition, Docencia en Red, Document translation, Efficient video subtitling, Machine Translation, MLLP, Post-editing, Video Lectures},
pubstate = {published},
tppubtype = {misc}
}

@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}
}