2014
|
Wuebker, Joern; Ney, Hermann; Martínez-Villaronga, Adrià; Giménez, Adrià; Juan, Alfons; Servan, Christophe; Dymetman, Marc; Mirkin, Shachar Comparison of Data Selection Techniques for the Translation of Video Lectures Inproceedings Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014), pp. 193–207, Vancouver (Canada), 2014. Links | BibTeX | Tags: @inproceedings{WueMarSer14,
title = {Comparison of Data Selection Techniques for the Translation of Video Lectures},
author = {Joern Wuebker and Hermann Ney and Adrià Martínez-Villaronga and Adrià Giménez and Alfons Juan and Christophe Servan and Marc Dymetman and Shachar Mirkin},
url = {https://aclanthology.org/2014.amta-researchers.15/},
year = {2014},
date = {2014-01-01},
booktitle = {Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014)},
pages = {193--207},
address = {Vancouver (Canada)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Valor Miró, Juan Daniel ; Spencer, R N; Pérez González de Martos, A; Garcés Díaz-Munío, G; Turró, C; Civera, J; Juan, A Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures Journal Article Open Learning: The Journal of Open, Distance and e-Learning, 29 (1), pp. 72–85, 2014. Abstract | Links | BibTeX | Tags: @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}
}
[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. |
Piqueras, S; del-Agua, M A; Giménez, A; Civera, J; Juan, A Statistical text-to-speech synthesis of Spanish subtitles Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. Links | BibTeX | Tags: @inproceedings{PiqAgu14,
title = {Statistical text-to-speech synthesis of Spanish subtitles},
author = {S. Piqueras and M. A. del-Agua and A. Giménez and J. Civera and A. Juan},
url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/paper3.pdf
http://link.springer.com/chapter/10.1007%2F978-3-319-13623-3_5},
year = {2014},
date = {2014-01-01},
booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)},
address = {Las Palmas de Gran Canaria (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Serrano, Nicolás; Civera, Jorge; Sanchis, Alberto; Juan, A Effective balancing error and user effort in interactive handwriting recognition Journal Article Pattern Recognition Letters, 37 , pp. 135–142, 2014. Links | BibTeX | Tags: @article{Serrano14b,
title = {Effective balancing error and user effort in interactive handwriting recognition},
author = {Nicolás Serrano and Jorge Civera and Alberto Sanchis and A. Juan},
url = {http://dx.doi.org/10.1016/j.patrec.2013.03.010},
year = {2014},
date = {2014-01-01},
journal = {Pattern Recognition Letters},
volume = {37},
pages = {135--142},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Pérez-González-de-Martos, A; Silvestre-Cerdá, J A; Rihtar, M; Juan, A; Civera, J Using Automatic Speech Transcriptions in Lecture Recommendation Systems Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. Links | BibTeX | Tags: @inproceedings{PerSil14,
title = {Using Automatic Speech Transcriptions in Lecture Recommendation Systems},
author = {A. Pérez-González-de-Martos and J. A. Silvestre-Cerdá and M. Rihtar and A. Juan and J. Civera},
url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/lavie_is2014_camready1.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)},
address = {Las Palmas de Gran Canaria (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
del-Agua, M A; Giménez, A; Serrano, N; Andrés-Ferrer, J; Civera, J; Sanchis, A; Juan, A The transLectures-UPV toolkit Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. Links | BibTeX | Tags: @inproceedings{AguGim14,
title = {The transLectures-UPV toolkit},
author = {M. A. del-Agua and A. Giménez and N. Serrano and J. Andrés-Ferrer and J. Civera and A. Sanchis and A. Juan},
url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/IberSpeech2014-TLK-camready1.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)},
address = {Las Palmas de Gran Canaria (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Martínez-Villaronga, A; del-Agua, M A; Silvestre-Cerdà, J A; Andrés-Ferrer, J; Juan, A Language model adaptation for lecture transcription by document retrieval Inproceedings Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014. Links | BibTeX | Tags: @inproceedings{MarAgu14,
title = {Language model adaptation for lecture transcription by document retrieval},
author = {A. Martínez-Villaronga and M. A. del-Agua and J.A. Silvestre-Cerdà and J. Andrés-Ferrer and A. Juan},
url = {http://www.mllp.upv.es/wp-content/uploads/2015/04/ibsp14-cameraReady.pdf},
year = {2014},
date = {2014-01-01},
booktitle = {Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)},
address = {Las Palmas de Gran Canaria (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Giménez, Adrià; Khoury, Ihab; Andrés-Ferrer, Jesús; Juan, Alfons Handwriting word recognition using windowed Bernoulli HMMs Journal Article Pattern Recognition Letters, 35 (0), pp. 149–156, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). Links | BibTeX | Tags: Sliding window @article{Giménez2014149,
title = {Handwriting word recognition using windowed Bernoulli HMMs},
author = {Adrià Giménez and Ihab Khoury and Jesús Andrés-Ferrer and Alfons Juan},
url = {http://dx.doi.org/10.1016/j.patrec.2012.09.002
http://hdl.handle.net/10251/37326},
issn = {0167-8655},
year = {2014},
date = {2014-01-01},
journal = {Pattern Recognition Letters},
volume = {35},
number = {0},
pages = {149--156},
note = {Frontiers in Handwriting Processing},
keywords = {Sliding window},
pubstate = {published},
tppubtype = {article}
}
|
Giménez, Adrià; Andrés-Ferrer, Jesús; Juan, Alfons Discriminative Bernoulli HMMs for isolated handwritten word recognition Journal Article Pattern Recognition Letters, 35 (0), pp. 157–168, 2014, ISSN: 0167-8655, (Frontiers in Handwriting Processing). Links | BibTeX | Tags: RIMES @article{Giménez2014157,
title = {Discriminative Bernoulli HMMs for isolated handwritten word recognition},
author = {Adrià Giménez and Jesús Andrés-Ferrer and Alfons Juan},
url = {http://dx.doi.org/10.1016/j.patrec.2013.05.016},
issn = {0167-8655},
year = {2014},
date = {2014-01-01},
journal = {Pattern Recognition Letters},
volume = {35},
number = {0},
pages = {157--168},
note = {Frontiers in Handwriting Processing},
keywords = {RIMES},
pubstate = {published},
tppubtype = {article}
}
|
Serrano, Nicolás; Giménez, Adrià; Civera, Jorge; Sanchis, Alberto; Juan, Alfons Interactive Handwriting Recognition with Limited User effort Journal Article Intl. Journal on Document Analysis and Recognition (IJDAR), 17 , pp. 47–59, 2014. Links | BibTeX | Tags: @article{Serrano14a,
title = {Interactive Handwriting Recognition with Limited User effort},
author = {Nicolás Serrano and Adrià Giménez and Jorge Civera and Alberto Sanchis and Alfons Juan},
url = {http://dx.doi.org/10.1007/s10032-013-0204-5},
year = {2014},
date = {2014-01-01},
journal = {Intl. Journal on Document Analysis and Recognition (IJDAR)},
volume = {17},
pages = {47--59},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Alabau, Vicent; Sanchis, Alberto; Casacuberta, Francisco Improving on-line handwritten recognition in interactive machine translation Journal Article Pattern Recognition, 47 (3) , pp. 1217–1228, 2014. Links | BibTeX | Tags: @article{valabau13c,
title = {Improving on-line handwritten recognition in interactive machine translation},
author = {Vicent Alabau and Alberto Sanchis and Francisco Casacuberta},
url = {http://dx.doi.org/10.1016/j.patcog.2013.09.035},
year = {2014},
date = {2014-01-01},
journal = {Pattern Recognition},
volume = {47 (3)},
pages = {1217--1228},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
2013
|
Martínez-Villaronga, Adrià Language model adaptation for video lecture transcription Masters Thesis Universitat Politècnica de València, 2013. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, language model adaptation, Video Lectures @mastersthesis{Martínez-Villaronga2013,
title = {Language model adaptation for video lecture transcription},
author = {Adrià Martínez-Villaronga},
url = {http://hdl.handle.net/10251/37114},
year = {2013},
date = {2013-09-25},
school = {Universitat Politècnica de València},
abstract = {In this work we propose a method to adapt language models to specific lectures in the context of video lecture automatic transcriptions. We explore different variations of the adaptation technique obtaining a significant WER reduction for the Spanish repository Polimedia.},
keywords = {Automatic Speech Recognition, language model adaptation, Video Lectures},
pubstate = {published},
tppubtype = {mastersthesis}
}
In this work we propose a method to adapt language models to specific lectures in the context of video lecture automatic transcriptions. We explore different variations of the adaptation technique obtaining a significant WER reduction for the Spanish repository Polimedia. |
Romero, Verónica; Fornés, Alicia; Serrano, Nicolás; Sánchez, Joan-Andreu; Toselli, Alejandro H; Frinken, Volkmar; Vidal, Enrique; Lladós, Josep The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition Journal Article Pattern Recognition, 46 (6), pp. 1658–1669, 2013. Links | BibTeX | Tags: @article{Romero13,
title = {The ESPOSALLES database: An ancient marriage license corpus for off-line handwriting recognition},
author = {Verónica Romero and Alicia Fornés and Nicolás Serrano and Joan-Andreu Sánchez and Alejandro H. Toselli and Volkmar Frinken and Enrique Vidal and Josep Lladós},
url = {http://dx.doi.org/10.1016/j.patcog.2012.11.024},
year = {2013},
date = {2013-01-01},
journal = {Pattern Recognition},
volume = {46},
number = {6},
pages = {1658–1669},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Alkhoury, Ihab; Giménez, Adrià; Juan, Alfons; Andrés-Ferrer, Jesús Arabic Printed Word Recognition Using Windowed Bernoulli HMMs Inproceedings Proc. of the 17th Intl. Conf. on Image, Analysis and Processings (ICIAP 2013), pp. 330 – 339, Naples (Italy), 2013. Links | BibTeX | Tags: @inproceedings{khoury13a,
title = {Arabic Printed Word Recognition Using Windowed Bernoulli HMMs},
author = {Ihab Alkhoury and Adrià Giménez and Alfons Juan and Jesús Andrés-Ferrer},
url = {http://dx.doi.org/10.1007/978-3-642-41181-6_34},
year = {2013},
date = {2013-01-01},
booktitle = {Proc. of the 17th Intl. Conf. on Image, Analysis and Processings (ICIAP 2013)},
pages = {330 -- 339},
address = {Naples (Italy)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Silvestre-Cerdà, Joan Albert; Pérez, Alejandro; Jiménez, Manuel; Turró, Carlos; Juan, Alfons; Civera, Jorge A System Architecture to Support Cost-Effective Transcription and Translation of Large Video Lecture Repositories Inproceedings Proc. of the IEEE Intl. Conf. on Systems, Man, and Cybernetics SMC 2013 , pp. 3994-3999, Manchester (UK), 2013. Abstract | Links | BibTeX | Tags: Accessibility, Automatic Speech Recognition, Education, Intelligent Interaction, Language Technologies, Machine Translation, Massive Adaptation, Multilingualism, Opencast Matterhorn, Video Lectures @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}
}
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. |
Martínez-Villaronga, A; del Agua, M A; Andrés-Ferrer, J; Juan, A Language model adaptation for video lectures transcription Inproceedings Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013, pp. 8450-8454, Vancouver (Canada), 2013. Links | BibTeX | Tags: language model adaptation, Video Lectures @inproceedings{Martinez-Villaronga2013,
title = {Language model adaptation for video lectures transcription},
author = {A. Martínez-Villaronga and M.A. del Agua and J. Andrés-Ferrer and A. Juan},
url = {http://dx.doi.org/10.1109/ICASSP.2013.6639314},
year = {2013},
date = {2013-01-01},
booktitle = {Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013},
pages = {8450-8454},
address = {Vancouver (Canada)},
keywords = {language model adaptation, Video Lectures},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Khoury, Ihab ; Giménez, Adrià ; Andrés-Ferrer, Jesús ; Juan, Alfons ; Sánchez, Joan Andreu The UPV Handwriting Recognition and Translation System for OpenHaRT 2013 Inproceedings Proc. of the NIST Open Handwriting Recognition and Translation Evaluation Workshop (OpenHaRT 2013), Washington DC (USA), 2013. Links | BibTeX | Tags: Arabic HTR, Bernoulli HMM, NIST OpenHaRT, Repositioning, Sliding window @inproceedings{Khoury2013,
title = {The UPV Handwriting Recognition and Translation System for OpenHaRT 2013},
author = {Khoury, Ihab and Giménez, Adrià and Andrés-Ferrer, Jesús and Juan, Alfons and Sánchez, Joan Andreu},
url = {http://www.nist.gov/itl/iad/mig/upload/OpenHaRT2013_SysDesc_UPV.pdf},
year = {2013},
date = {2013-01-01},
booktitle = {Proc. of the NIST Open Handwriting Recognition and Translation Evaluation Workshop (OpenHaRT 2013)},
address = {Washington DC (USA)},
keywords = {Arabic HTR, Bernoulli HMM, NIST OpenHaRT, Repositioning, Sliding window},
pubstate = {published},
tppubtype = {inproceedings}
}
|
2012
|
Silvestre-Cerdà, Joan Albert ; Del Agua, Miguel ; Garcés, Gonçal; Gascó, Guillem; Giménez-Pastor, Adrià; Martínez, Adrià; Pérez González de Martos, Alejandro ; Sánchez, Isaías; Serrano Martínez-Santos, Nicolás ; Spencer, Rachel; Valor Miró, Juan Daniel ; Andrés-Ferrer, Jesús; Civera, Jorge; Sanchís, Alberto; Juan, Alfons transLectures Inproceedings Proceedings (Online) of IberSPEECH 2012, pp. 345–351, Madrid (Spain), 2012. Abstract | Links | BibTeX | Tags: Accessibility, Automatic Speech Recognition, Education, Intelligent Interaction, Language Technologies, Machine Translation, Massive Adaptation, Multilingualism, Opencast Matterhorn, Video Lectures @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}
}
[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. |
Silvestre-Cerdà, Joan Albert; Giménez, Adrià; Andrés-Ferrer, Jesús; Civera, Jorge; Juan, Alfons Albayzin Evaluation: The PRHLT-UPV Audio Segmentation System Inproceedings Proceedings (Online) of IberSPEECH 2012, pp. 596-600, Madrid (Spain), 2012. Abstract | Links | BibTeX | Tags: @inproceedings{Silvestre-Cerdà2012c,
title = {Albayzin Evaluation: The PRHLT-UPV Audio Segmentation System},
author = {Joan Albert Silvestre-Cerdà and Adrià Giménez and Jesús Andrés-Ferrer and Jorge Civera and Alfons Juan},
url = {http://hdl.handle.net/10251/53699
http://iberspeech2012.ii.uam.es/IberSPEECH2012_OnlineProceedings.pdf},
year = {2012},
date = {2012-11-22},
booktitle = {Proceedings (Online) of IberSPEECH 2012},
pages = {596-600},
address = {Madrid (Spain)},
abstract = {This paper describes the audio segmentation system developed by the PRHLT research group at the UPV for the Albayzin Audio Segmentation Evaluation 2012. The PRHLT-UPV audio segmentation system is based on a conventional GMM-HMM speech recognition approach in which the vocabulary set is defined by the power set of segment classes. MFCC features were extracted to represent the acoustic signal and the AK toolkit was used for both, training acoustic models and performing audio segmentation. Experimental results reveals that our system provides an excellent performance on speech detection, so it could be successfully employed to provide speech segments to a diarization or speech recognition system.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper describes the audio segmentation system developed by the PRHLT research group at the UPV for the Albayzin Audio Segmentation Evaluation 2012. The PRHLT-UPV audio segmentation system is based on a conventional GMM-HMM speech recognition approach in which the vocabulary set is defined by the power set of segment classes. MFCC features were extracted to represent the acoustic signal and the AK toolkit was used for both, training acoustic models and performing audio segmentation. Experimental results reveals that our system provides an excellent performance on speech detection, so it could be successfully employed to provide speech segments to a diarization or speech recognition system. |
Martínez-Villaronga, Adrià Adaptació dels models de llenguatge per a la transcripció de vídeos de Polimedia Miscellaneous Final Year Project (Computer Science and Engineering at Universitat Politècnica de València), 2012. Links | BibTeX | Tags: Automatic Speech Recognition, language model adaptation @misc{Martínez-Villaronga2012,
title = {Adaptació dels models de llenguatge per a la transcripció de vídeos de Polimedia},
author = {Adrià Martínez-Villaronga},
url = {http://hdl.handle.net/10251/16936},
year = {2012},
date = {2012-07-30},
howpublished = {Final Year Project (Computer Science and Engineering at Universitat Politècnica de València)},
keywords = {Automatic Speech Recognition, language model adaptation},
pubstate = {published},
tppubtype = {misc}
}
|
Doetsch, Patrick; Hamdani, Mahdi; Giménez-Pastor, Adrià; Andrés-Ferrer, Jesús; Juan, Alfons; Ney, Hermann Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition Inproceedings Proc. of the 2012 Intl. Conf. on Frontiers in Handwriting Recognition (ICFHR 2012), pp. 3 – 7, 2012. BibTeX | Tags: @inproceedings{doetsch12,
title = {Comparison of Bernoulli and Gaussian HMMs using a vertical repositioning technique for off-line handwriting recognition},
author = {Patrick Doetsch and Mahdi Hamdani and Adrià Giménez-Pastor and Jesús Andrés-Ferrer and Alfons Juan and Hermann Ney},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of the 2012 Intl. Conf. on Frontiers in Handwriting Recognition (ICFHR 2012)},
pages = {3 -- 7},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Valor Miró, Juan Daniel ; Pérez González de Martos, Alejandro ; Civera, Jorge ; Juan, Alfons Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform Incollection Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012), 328 , pp. 237-246, Springer Berlin Heidelberg, 2012, ISBN: 978-3-642-35291-1, (doi: 10.1007/978-3-642-35292-8_20). Links | BibTeX | Tags: Google N-Gram, Language Modeling, Linear Combination, Opencast Matterhorn, Speech Recognition @incollection{Valor2012,
title = {Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform},
author = {Valor Miró, Juan Daniel and Pérez González de Martos, Alejandro and Civera, Jorge and Juan, Alfons},
url = {http://hdl.handle.net/10251/35190
http://www.mllp.upv.es/wp-content/uploads/2015/04/paper2.pdf},
isbn = {978-3-642-35291-1},
year = {2012},
date = {2012-01-01},
booktitle = {Advances in Speech and Language Technologies for Iberian Languages (IberSpeech 2012)},
volume = {328},
pages = {237-246},
publisher = {Springer Berlin Heidelberg},
series = {Communications in Computer and Information Science},
note = {doi: 10.1007/978-3-642-35292-8_20},
keywords = {Google N-Gram, Language Modeling, Linear Combination, Opencast Matterhorn, Speech Recognition},
pubstate = {published},
tppubtype = {incollection}
}
|
Silvestre-Cerdà, Joan Albert; Andrés-Ferrer, Jesús; Civera, Jorge Explicit length modelling for statistical machine translation Journal Article Pattern Recognition, 45 (9), pp. 3183 - 3192, 2012, ISSN: 0031-3203. Abstract | Links | BibTeX | Tags: Length modelling, Log-linear models, Phrase-based models, Statistical machine translation @article{Silvestre-Cerdà2012a,
title = {Explicit length modelling for statistical machine translation},
author = {Joan Albert Silvestre-Cerdà and Jesús Andrés-Ferrer and Jorge Civera},
url = {http://hdl.handle.net/10251/34996},
issn = {0031-3203},
year = {2012},
date = {2012-01-01},
journal = {Pattern Recognition},
volume = {45},
number = {9},
pages = {3183 - 3192},
abstract = {Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling.},
keywords = {Length modelling, Log-linear models, Phrase-based models, Statistical machine translation},
pubstate = {published},
tppubtype = {article}
}
Explicit length modelling has been previously explored in statistical pattern recognition with successful results. In this paper, two length models along with two parameter estimation methods and two alternative parametrisation for statistical machine translation (SMT) are presented. More precisely, we incorporate explicit bilingual length modelling in a state-of-the-art log-linear SMT system as an additional feature function in order to prove the contribution of length information. Finally, a systematic evaluation on reference SMT tasks considering different language pairs prove the benefits of explicit length modelling. |
Ortiz-Martínez, Daniel; Sanchis-Trilles, Germán; Casacuberta, Francisco; Alabau, Vicent; Vidal, Enrique; Benedí, José-Miguel; González-Rubio, Jesús; Sanchis, Alberto; González, Jorge The CASMACAT Project: The Next Generation Translator’s Workbench Inproceedings Proceedings of IberSPEECH 2012, pp. 326-334, Madrid (Spain), 2012. BibTeX | Tags: @inproceedings{Ortiz-Martínez2012,
title = {The CASMACAT Project: The Next Generation Translator’s Workbench},
author = {Daniel Ortiz-Martínez and Germán Sanchis-Trilles and Francisco Casacuberta and Vicent Alabau and Enrique Vidal and José-Miguel Benedí and Jesús González-Rubio and Alberto Sanchis and Jorge González},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of IberSPEECH 2012},
pages = {326-334},
address = {Madrid (Spain)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
González-Rubio, Jesús; Sanchis, Alberto; Casacuberta, Francisco PRHLT Submission to the WMT12 Quality Estimation Task Inproceedings Proceedings of the Seventh Workshop on Statistical Machine Translation, pp. 104–108, North American Chapter of the Association for Computational Linguistics Association for Computational Linguistics, 2012. BibTeX | Tags: @inproceedings{gonzalezrubio2012b,
title = {PRHLT Submission to the WMT12 Quality Estimation Task},
author = {Jesús González-Rubio and Alberto Sanchis and Francisco Casacuberta},
year = {2012},
date = {2012-01-01},
booktitle = {Proceedings of the Seventh Workshop on Statistical Machine Translation},
pages = {104--108},
publisher = {Association for Computational Linguistics},
organization = {North American Chapter of the Association for Computational Linguistics},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Sanchis, Alberto; Juan, Alfons; Vidal, Enrique A Word-Based Naïve Bayes Classifier for Confidence Estimation in Speech Recognition Journal Article IEEE Transactions on Audio, Speech, and Language Processing, 20 (2), pp. 565-574, 2012. Links | BibTeX | Tags: @article{,
title = {A Word-Based Naïve Bayes Classifier for Confidence Estimation in Speech Recognition},
author = {Alberto Sanchis and Alfons Juan and Enrique Vidal},
url = {http://dx.doi.org/10.1109/TASL.2011.2162403
http://hdl.handle.net/10251/36083},
year = {2012},
date = {2012-01-01},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
volume = {20},
number = {2},
pages = {565-574},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
Khoury, Ihab; Giménez-Pastor, Adrià; Juan, Alfons Guide to OCR for Arabic Scripts Book Chapter Märgner Volkerand El Abed, Haikal (Ed.): Chapter Arabic Handwriting Recognition Using Ber, pp. 255-272, Springer, 2012. BibTeX | Tags: @inbook{Khoury12-AHRBook-chp10,
title = {Guide to OCR for Arabic Scripts},
author = {Ihab Khoury and Adrià Giménez-Pastor and Alfons Juan},
editor = {Märgner, Volkerand El Abed, Haikal },
year = {2012},
date = {2012-01-01},
pages = {255-272},
publisher = {Springer},
chapter = {Arabic Handwriting Recognition Using Ber},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
|
Gascó, Guillem; Rocha, Martha-Alicia ; Sanchis-Trilles, Germán ; Andrés-Ferrer, Jesús ; Casacuberta, Francisco Does more data always yield better translations? Inproceedings Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012), pp. 152–161, Association for Computational Linguistics, Avignon (France), 2012. Links | BibTeX | Tags: @inproceedings{gasco-EtAl:2012:EACL2012,
title = {Does more data always yield better translations?},
author = { Guillem Gascó and Martha-Alicia Rocha and Germán Sanchis-Trilles and Jesús Andrés-Ferrer and Francisco Casacuberta},
url = {http://hdl.handle.net/10251/35214},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012)},
pages = {152--161},
publisher = {Association for Computational Linguistics},
address = {Avignon (France)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Turró, Carlos; Juan, Alfons; Civera, Jorge; Orliĉ, Davor; Jermol, Mitja transLectures: Transcription and Translation of Video Lectures Inproceedings Proc. of Cambridge 2012: Innovation and Impact - Openly Collaborating to Enhance Education, pp. 543-546, Cambridge (UK), 2012. Abstract | Links | BibTeX | Tags: Automatic Speech Recognition, Statistical machine translation @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}
}
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. |
Romero, Verónica; Sánchez, Joan-Andreu; Serrano, Nicolás; Vidal, Enrique Evaluating a post-editing approach for handwriting transcription Inproceedings Proc. of the Conf. on Natural Language Processing KONVENS 2012 (Language Technology for Historical Text Workshop), pp. 357-364, 2012. BibTeX | Tags: @inproceedings{Romero12,
title = {Evaluating a post-editing approach for handwriting transcription},
author = {Verónica Romero and Joan-Andreu Sánchez and Nicolás Serrano and Enrique Vidal},
year = {2012},
date = {2012-01-01},
booktitle = {Proc. of the Conf. on Natural Language Processing KONVENS 2012 (Language Technology for Historical Text Workshop)},
pages = {357-364},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|