Publications

@phdthesis{Garcés2024,
title = {Automatic speech recognition and machine translation with deep neural networks for open educational resources, parliamentary contents and broadcast media},
author = {Garcés Díaz-Munío, Gonçal},
url = {https://www.upv.es/pls/oalu/sic_ted.mostrar_tesis?p_num_reg=12900
https://www.mllp.upv.es/phd-thesis-automatic-speech-recognition-and-machine-translation-with-deep-neural-networks-for-open-educational-resources-parliamentary-contents-and-broadcast-media-by-goncal-garces/},
year = {2024},
date = {2024-01-01},
school = {Universitat Politècnica de València},
abstract = {In the last decade, automatic speech recognition (ASR) and machine translation (MT) have improved enormously through the use of constantly evolving deep neural network (DNN) models. If at the beginning of the 2010s the then pre-DNN ASR and MT systems were ready to tackle with success some real-life applications such as offline video lecture transcription and translation, now in the 2020s much more challenging applications are within grasp, such as live broadcast media subtitling. At the same time in this period, media accessibility for everyone, including deaf and hard-of-hearing people, is being given more and more importance. ASR and MT, in their current state, are powerful tools to increase the coverage of accessibility measures such as subtitles, transcriptions and translations, also as a way of providing multilingual access to all types of content. In this PhD thesis, we present research results on automatic speech recognition and machine translation based on deep neural networks in three very active domains: open educational resources, parliamentary contents and broadcast media. Regarding open educational resources (OER), we first present work on the evaluation and post-editing of ASR and MT with intelligent interaction approaches, as carried out in the framework of EU project transLectures: Transcription and Translation of Video Lectures. The results obtained confirm that the intelligent interaction approach can make post-editing automatic transcriptions and translations even more cost-effective. Then, in the context of subsequent EU project X5gon, we present research on developing DNN-based neural MT systems, and making the most of larger MT corpora through automatic data filtering. This work resulted in a first-rank classification in an international evaluation campaign on MT, and we show how these new NMT systems improved the quality of multilingual subtitles in real OER scenarios. In the also growing domain of language technologies for parliamentary contents, we describe research on speech data curation techniques for streaming ASR in the context of European Parliament debates. This research resulted in the release of Europarl-ASR, a new, large speech corpus for streaming ASR system training and evaluation, as well as for the benchmarking of speech data curation techniques. Finally, we present work in a domain on the edge of the state of the art for ASR and MT: the live subtitling of broadcast media, in the context of the 2020–2023 R&D collaboration agreement between the Valencian public broadcaster À Punt and the Universitat Politècnica de València for real-time computer assisted subtitling of media contents. This research has resulted in the deployment of high-quality, low-latency, real-time streaming ASR systems for a less-spoken language (Catalan) and a widely spoken language (Spanish) in a real broadcast use case.},
note = {advisers: Alfons Juan Ciscar and Jorge Civera Saiz},
keywords = {Automatic Speech Recognition, Broadcast Media, Deep Neural Networks, Machine Translation, Open Educational Resources, Parliamentary Contents},
pubstate = {published},
tppubtype = {phdthesis}
}

@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{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. Conf. 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}
}

@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}
}

@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}
}

@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}
}

@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}
}

@inproceedings{Iranzo-Sánchez2019,
title = {The MLLP-UPV Supervised Machine Translation Systems for WMT19 News Translation Task},
author = {Iranzo-Sánchez, Javier and Garcés Díaz-Munío, Gonçal V. and Civera, Jorge and Juan, Alfons},
url = {https://www.mllp.upv.es/wp-content/uploads/2019/09/poster-1.pdf},
doi = {10.18653/v1/W19-5320},
year = {2019},
date = {2019-01-01},
booktitle = {Proc. of Fourth Conference on Machine Translation (WMT19)},
pages = {218-224},
address = {Florence (Italy)},
abstract = {[EN] This paper describes the participation of the MLLP research group of the Universitat Politècnica de València in the WMT 2019 News Translation Shared Task. In this edition, we have submitted systems for the German ↔ English and German ↔ French language pairs, participating in both directions of each pair. Our submitted systems, based on the Transformer architecture, make ample use of data filtering, synthetic data and domain adaptation through fine-tuning.

[CA] "Els sistemes de traducció automàtica supervisada de l'MLLP-UPV per a la tasca de traducció de notícies de WMT19": En aquest article descrivim la participació del grup de recerca MLLP de la Universitat Politècnica de València en la competició de traducció de notícies de WMT 2019. En aquesta edició, hem presentat sistemes per a les combinacions de traducció alemany ↔ anglés i alemany ↔ francés (en ambdós sentits). Els sistemes presentats, basats en l'arquitectura Transformer, fan un ús extens del filtratge de dades, les dades sintètiques i l'ajust fi amb adaptació al domini.},
keywords = {Machine Translation, Neural Machine Translation, WMT19 News Translation},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Iranzo-Sánchez2018,
title = {The MLLP-UPV German-English Machine Translation System for WMT18},
author = {Iranzo-Sánchez, Javier and Baquero-Arnal, Pau and Garcés Díaz-Munío, Gonçal V. and Martínez-Villaronga, Adrià and Civera, Jorge and Juan, Alfons},
url = {http://dx.doi.org/10.18653/v1/W18-6414
https://www.mllp.upv.es/wp-content/uploads/2018/11/wmt18_mllp-upv_poster.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {Proc. of the Third Conference on Machine Translation (WMT18), Volume 2: Shared Task Papers},
pages = {422--428},
address = {Brussels (Belgium)},
abstract = {[EN] This paper describes the statistical machine translation system built by the MLLP research group of Universitat Politècnica de València for the German>English news translation shared task of the EMNLP 2018 Third Conference on Machine Translation (WMT18). We used an ensemble of Transformer architecture–based neural machine translation systems. To train our system under "constrained" conditions, we filtered the provided parallel data with a scoring technique using character-based language models, and we added parallel data based on synthetic source sentences generated from the provided monolingual corpora.

[CA] "El sistema de traducció automàtica alemany>anglés de l'MLLP-UPV per a WMT18": En aquest article descrivim el sistema de traducció automàtica estadística creat pel grup d'investigació MLLP de la Universitat Politècnica de València per a la competició de traducció de notícies alemany>anglés de la Third Conference on Machine Translation (WMT18, associada a la conferència EMNLP 2018). Hem utilitzat una combinació de sistemes de traducció automàtica neuronal basats en l'arquitectura Transformer. Per a entrenar el nostre sistema en la categoria "fitada" (només amb els corpus lingüístics oficials de la competició), hem filtrat les dades paral·leles disponibles amb una tècnica que assigna puntuacions utilitzant models de llenguatge de caràcters, i hem afegit dades paral·leles basades en frases d'origen sintètiques generades a partir dels corpus monolingües disponibles.},
keywords = {Data Selection, Machine Translation, Neural Machine Translation, WMT18 news translation},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Lafuente2017,
title = {Several approaches for tweet topic classification in COSET – IberEval 2017},
author = {Villar Lafuente, Carlos and Garcés Díaz-Munío, Gonçal},
url = {http://hdl.handle.net/10251/166361
http://ceur-ws.org/Vol-1881/COSET_paper_4.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Proc. of 2nd Workshop on Evaluation of Human Language Technologies for Iberian Languages (IberEval 2017)},
pages = {36--42},
address = {Murcia (Spain)},
abstract = {[EN] These working notes summarize the different approaches we have explored in order to classify a corpus of tweets related to the 2015 Spanish General Election (COSET 2017 task from IberEval 2017). Two approaches were tested during the COSET 2017 evaluations: Neural Networks with Sentence Embeddings (based on TensorFlow) and N-gram Language Models (based on SRILM). Our results with these approaches were modest: both ranked above the “Most frequent" baseline, but below the “Bag-of-words + SVM” baseline. A third approach was tried after the COSET 2017 evaluation phase was over: Advanced Linear Models (based on fastText). Results measured over the COSET 2017 Dev and Test show that this approach is well above the “TF-IDF+RF” baseline.

[CA] "Alguns mètodes per a la classificació temàtica de tuits en COSET - IberEval 2017": Aquest article resumeix els diferents mètodes que hem explorat per a classificar un corpus de tuits sobre les eleccions generals d'Espanya de 2015 (tasca COSET 2017 del taller IberEval 2017). Analitzàrem dos mètodes durant les avaluacions de COSET 2017: xarxes neuronals amb vectorització ("embedding") a nivell de frase (basat en TensorFlow) i models de llenguatge d'n-grames (basat en SRILM). Els nostres resultats amb aquests mètodes van ser modests: ambdós quedaren per damunt del valor de referència d'"el més freqüent" ("Most frequent"), però per davall del valor de referència de "bossa de paraules+SVM" ("Bag-of-words+SVM"). Analitzàrem un tercer mètode quan ja havia acabat la fase d'avaluacions de COSET 2017: models lineals avançats (basat en fastText). Els resultats mesurats sobre els conjunts de validació i prova de COSET 2017 mostren que aquest mètode supera clarament el valor de referència "TF-IDF+RF".},
keywords = {COSET2017, language models, linear models, neural networks, sentence embeddings, text classification},
pubstate = {published},
tppubtype = {inproceedings}
}

@inproceedings{Valor14-InRed,
title = {Evaluación del proceso de revisión de transcripciones automáticas para vídeos Polimedia},
author = {Valor Miró, Juan Daniel and Spencer, R.N. and Pérez González de Martos, A. and Garcés Díaz-Munío, G. and Turró, C. and Civera, J. and Juan, A.},
url = {http://hdl.handle.net/10251/40404
http://dx.doi.org/10.4995/INRED.2014
http://www.mllp.upv.es/wp-content/uploads/2015/04/paper1.pdf
https://www.mllp.upv.es/wp-content/uploads/2019/09/poster.pdf},
year = {2014},
date = {2014-07-01},
booktitle = {Proc. of I Jornadas de Innovación Educativa y Docencia en Red (IN-RED 2014)},
pages = {272--278},
address = {Valencia (Spain)},
abstract = {[EN] Video lectures are a tool of proven value and wide acceptance in universities which is leading to video lecture platforms like poliMèdia (Universitat Politècnica de València). transLectures is an EU project that generates high-quality automatic transcriptions and translations for the poliMèdia platform, and improves them by using massive adaptation and intelligent interaction techniques. In this paper we present the evaluation with lecturers carried out under the Docència en Xarxa 2012-2013 action plan with the aim of studying the process of transcription post-editing, in contrast with transcribing from scratch.

[ES] Los vídeos docentes son una herramienta de demostrada utilidad y gran aceptación en el mundo universitario que está dando lugar a plataformas de vídeos docentes como poliMèdia (Universitat Politècnica de València). transLectures es un proyecto europeo que genera transcripciones y traducciones automáticas de alta calidad para la plataforma poliMèdia, mediante técnicas de adaptación masiva e interacción inteligente. En este artículo presentamos la evaluación con profesores que se realizó en el marco del plan de acción Docència en Xarxa 2012-2013, con el objetivo de estudiar el proceso de supervisión de transcripciones, comparándolo con la obtención de la transcripción sin disponer de una transcripción automática previa.

[CA] Els vídeos docents són una eina d'utilitat demostrada i amb gran acceptació en el món universitari que està donant lloc a plataformes de vídeos docents com poliMèdia (Universitat Politècnica de València). transLectures és un projecte europeu que genera transcripcions i traduccions automàtiques d'alta qualitat per a la plataforma poliMèdia, mitjançant tècniques d'adaptació massiva i interacció intel·ligent. En aquest article presentem l'avaluació amb professors que es realitzà en el marc del pla d'acció Docència en Xarxa 2012-2013, amb l'objectiu d'estudiar el procés de supervisió de transcripcions, comparant-lo amb l'obtenció de la transcripció sense disposar d'una transcripció automàtica prèvia.},
keywords = {ASR, Docencia en Red, evaluaciones, Polimedia, transcripciones},
pubstate = {published},
tppubtype = {inproceedings}
}

@article{doi:10.1080/02680513.2014.909722,
title = {Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures},
author = {Valor Miró, Juan Daniel and Spencer, R.N. and Pérez González de Martos, A. and Garcés Díaz-Munío, G. and Turró, C. and Civera, J. and Juan, A.},
url = {http://hdl.handle.net/10251/55925
http://dx.doi.org/10.1080/02680513.2014.909722
http://www.mllp.upv.es/wp-content/uploads/2015/04/author_version.pdf},
year = {2014},
date = {2014-01-01},
journal = {Open Learning: The Journal of Open, Distance and e-Learning},
volume = {29},
number = {1},
pages = {72--85},
abstract = {[EN] Video lectures are fast becoming an everyday educational resource in higher education. They are being incorporated into existing university curricula around the world, while also emerging as a key component of the open education movement. In 2007 the Universitat Politècnica de València (UPV) implemented its poliMèdia lecture capture system for the creation and publication of quality educational video content and now has a collection of over 10,000 video objects. In 2011 it embarked on the EU-subsidised transLectures project to add automatic subtitles to these videos in both Spanish and other languages. By doing so, it allows access to their educational content by non-native speakers and the deaf and hard-of-hearing, as well as enabling advanced repository management functions. In this paper, following a short introduction to poliMèdia, transLectures and Docència en Xarxa, the UPV's action plan to boost the use of digital resources at the university, we will discuss the three-stage evaluation process carried out with the collaboration of UPV lecturers to find the best interaction protocol for the task of post-editing automatic subtitles.

[CA] "Avaluació d'interfícies intel·ligents per a la postedició de transcripcions automàtiques de vídeos docents en línia": Els vídeos docents s'estan convertint en un recurs d'ús quotidià en l'educació superior. Estan entrant en els plans d'estudis universitaris de tot el món, al mateix temps que es defineixen com un component clau del moviment de l'educació lliure. L'any 2007, la Universitat Politècnica de València (UPV) implementà el seu sistema d'enregistrament de classes poliMèdia, que permet la producció i publicació de continguts audiovisuals d'alta qualitat, i que ja acumula més de 10.000 vídeos. L'any 2011, la UPV va entrar en el projecte europeu transLectures per a afegir subtítols automàtics a aquests vídeos en castellà, català i altres llengües. Així, es facilita l'accés a aquests continguts educatius per part de parlants d'altres llengües i de persones sordes o amb dificultats auditives, i també es proporcionen funcions avançades de gestió del repositori. En aquest article, després de presentar poliMèdia, transLectures i Docència en Xarxa (el pla d'acció de la UPV per a impulsar l'ús de recursos digitals en la universitat), explicarem el procés d'avaluació en tres fases que s'ha realitzat amb la col·laboració de professors de la UPV per a trobar el millor protocol d'interacció per a la postedició de subtítols automàtics.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@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}
}