Publications

@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{valor2015efficient,
title = {Efficient Generation of High-Quality Multilingual Subtitles for Video Lecture Repositories},
author = {Valor Miró, Juan Daniel and Silvestre-Cerdà, Joan Albert and Civera, Jorge and Turró, Carlos and Juan, Alfons},
url = {http://link.springer.com/chapter/10.1007/978-3-319-24258-3_44
http://www.mllp.upv.es/wp-content/uploads/2016/03/paper.pdf
},
isbn = {978-3-319-24258-3},
year = {2015},
date = {2015-09-17},
booktitle = {Proc. of 10th European Conf. on Technology Enhanced Learning (EC-TEL 2015)},
pages = {485--490},
address = {Toledo (Spain)},
abstract = {Video lectures are a valuable educational tool in higher education to support or replace face-to-face lectures in active learning strategies. In 2007 the Universitat Polit‘ecnica de Val‘encia (UPV) implemented its video lecture capture system, resulting in a high quality educational video repository, called poliMedia, with more than 10.000 mini lectures created by 1.373 lecturers. Also, in the framework of the European project transLectures, UPV has automatically generated transcriptions and translations in Spanish, Catalan and English for all videos included in the poliMedia video repository. transLectures’s objective responds to the widely-recognised need for subtitles to be provided with video lectures, as an essential service for non-native speakers and hearing impaired persons, and to allow advanced repository functionalities. Although high-quality automatic transcriptions and translations were generated in transLectures, they were not error-free. For this reason, lecturers need to manually review video subtitles to guarantee the absence of errors. The aim of this study is to evaluate the efficiency of the manual review process from automatic subtitles in comparison with the conventional generation of video subtitles from scratch. The reported results clearly indicate the convenience of providing automatic subtitles as a first step in the generation of video subtitles and the significant savings in time of up to almost 75% involved in reviewing subtitles.},
keywords = {Automatic Speech Recognition, Docencia en Red, Efficient video subtitling, Polimedia, Statistical machine translation, video lecture repositories},
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}
}