Progress

Deliverables

In this section of the website, you will find more technical information about the project and its key areas of research, presented by Work Package.

We will also be making all public reports and deliverables available for download here.

transLectures project overview video

Intelligent interaction demo

We are excited to present our latest demo video, shown for the first time at the 2013 European Semantic Web Conference. In it, you can see the new intelligent interaction mode currently being tested by our first groups of users. UPVLC researcher, Alex Perez, guides us through the process.

Integration into Matterhorn infrastructure

Here we present a short demo of what transLectures tools will look like when they are up-and-running on the Matterhorn platform. In the first part of the video, we see how the videos will be processed “behind the scenes” in order to obtain their transcriptions and translations. Then, we see how the intelligent interaction element of the project will materialise itself, watching as a user edits key sections of the automatic transcript and add corrections in real time.

Text-to-Speech English demo

Publications

Here is the list of publications related to the transLectures project.

2016

  • [PDF] I. Sanchez-Cortina, J. Andrés-Ferrer, A. Sanchis, and A. Juan, “Speaker-adapted confidence measures for speech recognition of video lectures,” Computer Speech & Language, vol. 37, pp. 11-23, 2016.
    [Bibtex]
    @article{SanchezCortina201611,
    author = {Isaias Sanchez-Cortina and Jesús Andrés-Ferrer and Alberto Sanchis and Alfons Juan},
    title = {{Speaker-adapted confidence measures for speech recognition of video lectures}},
    journal = {Computer Speech & Language},
    volume = {37},
    pages = {11 -- 23},
    year = {2016},
    note = {forthcoming},
    issn = {0885-2308},
    keywords = {Confidence measures},
    keywords = {Speech recognition},
    keywords = {Speaker adaptation},
    keywords = {Log-linear models},
    keywords = {Online video lectures},
    pdf = {},
    url = {http://www.sciencedirect.com/science/article/pii/S0885230815000960},
    doi = {10.1016/j.csl.2015.10.003},
    hdl = {}
    }

2015

  • [PDF] [PDF] M. Á. del-Agua, A. Martínez-Villaronga, S. Piqueras, A. Giménez, A. Sanchis, J. Civera, and A. Juan, “The MLLP ASR Systems for IWSLT 2015,” in Proc. of 12th Intl. Workshop on Spoken Language Translation (IWSLT 2015), Da Nang (Vietnam), 2015, pp. 39-44.
    [Bibtex]
    @inproceedings{delAgua15,
      booktitle={Proc. of 12th Intl. Workshop on Spoken Language Translation (IWSLT 2015)},
      title={{The MLLP ASR Systems for IWSLT 2015}},
      author={del-Agua, Miguel Ángel and Martínez-Villaronga, Adrià and Piqueras, Santiago and Giménez, Adrià and Sanchis, Alberto and Civera, Jorge and Juan, Alfons},
      pages={39-44},
      month=dec,
      year={2015},
      address={Da Nang (Vietnam)},
      pdf={http://workshop2015.iwslt.org/downloads/proceeding.pdf},
      url={http://workshop2015.iwslt.org/64.php},
      doi={},
      hdl={}
    }
  • [PDF] [PDF] C. Servan and M. Dymetman, “Adaptation par enrichissement terminologique en traduction automatique statistique fondée sur la génération et le filtrage de bi-segments virtuels,” in Proc. of 22ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2015), Caen (France), 2015, pp. 384-390.
    [Bibtex]
    @inproceedings{servan-dymetman:2015:TALN,
      booktitle={Proc. of 22\`eme Conf\'erence sur le Traitement Automatique des Langues Naturelles (TALN 2015)},
      title={{Adaptation par enrichissement terminologique en traduction automatique statistique fond\'ee sur la g\'en\'eration et le filtrage de bi-segments virtuels}},
      author={Servan, Christophe and Dymetman, Marc},
      pages={384--390},
      month=jun,
      year={2015},
      address={Caen (France)},
      pdf={https://hal.archives-ouvertes.fr/hal-01157850/document},
      url={http://www.atala.org/taln_archives/TALN/TALN-2015/taln-2015-court-011.html},
      doi={}
    }
  • [PDF] J. D. Valor Miró, J. A. Silvestre-Cerdà, J. Civera, C. Turró, and A. Juan, “Efficiency and usability study of innovative computer-aided transcription strategies for video lecture repositories,” Speech Communication, vol. 74, pp. 65-75, 2015.
    [Bibtex]
    @article{Valor201565,
    author = {Valor Miró, Juan Daniel and Silvestre-Cerdà, Joan Albert and Civera, Jorge and Turró,Carlos and Juan, Alfons},
    title = {{Efficiency and usability study of innovative computer-aided transcription strategies for video lecture repositories}},
    journal = {Speech Communication},
    volume = {74},
    pages = {65--75},
    year = {2015},
    issn = {0167-6393},
    pdf = {},
    url = {http://www.sciencedirect.com/science/article/pii/S0167639315001016},
    doi = {10.1016/j.specom.2015.09.006},
    hdl = {},
    keywords = {Video lecture repositories},
    keywords = {Usability study},
    keywords = {Computer-assisted transcription},
    keywords = {Interface design strategies},
    keywords = {Automatic speech recognition}
    }
  • [PDF] J. D. Valor Miró, J. A. Silvestre-Cerdà, J. Civera, C. Turró, and A. Juan, “Efficient Generation of High-Quality Multilingual Subtitles for Video Lecture Repositories,” in Proc. of EC-TEL 2015: Design for Teaching and Learning in a Networked World, Toledo (Spain), 2015, pp. 485-490.
    [Bibtex]
    @inproceedings{Valor15-ECTEL,
    booktitle={Proc. of EC-TEL 2015: Design for Teaching and Learning in a Networked World},
    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},
    pages={485--490},
    volume={9307},
    series={Lecture Notes in Computer Science},
    year={2015},
    address={Toledo (Spain)},
    publisher={Springer International Publishing},
    keywords={Video lecture repositories; Automatic speech recognition; Machine translation; Efficient video subtitling},
    pdf={},
    url={http://link.springer.com/chapter/10.1007%2F978-3-319-24258-3_44},
    doi={10.1007/978-3-319-24258-3_44},
    hdl={}
    }
  • [PDF] [PDF] J. D. Valor Miró, C. Turró, J. Civera, and A. Juan, “Evaluación de la revisión de transcripciones y traducciones automáticas de vídeos Polimedia,” in Proc. of I Congreso Nacional de Innovación Educativa y Docencia en Red (IN-RED 2015), València (Spain), 2015, pp. 464-468.
    [Bibtex]
    @INPROCEEDINGS{Valor15-InRed,
      author = {Valor Miró, J.D. and Turró, C. and Civera, J. and Juan, A.},
      booktitle = {Proc. of I Congreso Nacional de Innovación Educativa y Docencia en Red (IN-RED 2015)},
      title = {{Evaluación de la revisión de transcripciones y traducciones automáticas de vídeos Polimedia}},
      year = {2015},
      month = jun,
      address = {Val\`encia (Spain)},
      pages= {464--468},
      keywords = {transcripciones; traducciones; evaluaciones con usuario; Docencia en Red; Polimedia},
      pdf={http://ocs.editorial.upv.es/index.php/INRED/INRED2015/paper/view/1574/414},
      url={http://hdl.handle.net/10251/52755},
      doi={10.4995/INRED2015.2015.1574},
      hdl={http://hdl.handle.net/10251/52755}
    }

2014

  • [PDF] [PDF] M. A. del-Agua, A. Giménez, N. Serrano, J. Andrés-Ferrer, J. Civera, A. Sanchis, and A. Juan, “The transLectures-UPV toolkit,” in Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages, Las Palmas de Gran Canaria (Spain), 2014, pp. 269-278.
    [Bibtex]
    @inproceedings{AguGim14,
      booktitle={Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages},
      title={{The transLectures-UPV toolkit}},
      author={M. A. del-Agua and A. Gim\'enez and N. Serrano and J. Andr\'es-Ferrer and J. Civera and A. Sanchis and A. Juan},
      pages={269--278},
      volume={8854},
      series={Lecture Notes in Computer Science},
      month=nov,
      year={2014},
      address={Las Palmas de Gran Canaria (Spain)},
      pdf={http://riunet.upv.es/bitstream/handle/10251/50452/IberSpeech2014-TLK-camready.pdf},
      url={http://hdl.handle.net/10251/50452},
      doi={10.1007/978-3-319-13623-3_28},
      hdl={http://hdl.handle.net/10251/50452}
    }
  • [PDF] [PDF] A. Martínez-Villaronga, M. A. del-Agua, J. Andrés-Ferrer, and A. Juan, “Language model adaptation for lecture transcription by document retrieval,” in Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages, Las Palmas de Gran Canaria (Spain), 2014, pp. 129-137.
    [Bibtex]
    @inproceedings{MarAgu14,
      booktitle={Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages},
      title={{Language model adaptation for lecture transcription by document retrieval}},
      author={A. Mart\'inez-Villaronga and M. A. del-Agua and J. Andr\'es-Ferrer and A. Juan},
      pages={129--137},
      volume={8854},
      series={Lecture Notes in Computer Science},
      month=nov,
      year={2014},
      address={Las Palmas de Gran Canaria (Spain)},
      pdf={https://riunet.upv.es/bitstream/handle/10251/50657/ibsp14-cameraReady.pdf},
      url={http://hdl.handle.net/10251/50657},
      doi={10.1007/978-3-319-13623-3_14},
      hdl={http://hdl.handle.net/10251/50657}
    }
  • [PDF] [PDF] S. Mirkin, “Incrementally Updating the SMT Reordering Model,” in Proc. of the 28th Pacific Asia Conference on Language, Information and Computing (PACLIC 2014), Phuket (Thailand), 2014, pp. 272-281.
    [Bibtex]
    @inproceedings{mirkin14:paclic,
      author= {Mirkin, Shachar},
      title= {{Incrementally Updating the SMT Reordering Model}},
      booktitle= {Proc. of the 28th Pacific Asia Conference on Language, Information and Computing (PACLIC 2014)},
      year= {2014},
      month= dec,
      pages= {272--281},
      address= {Phuket (Thailand)},
      pdf= {http://www.aclweb.org/anthology/Y14-1033},
      url= {http://www.arts.chula.ac.th/~ling/paclic28/proceedings.html},
      doi= {}
    }
  • [PDF] D. Orlic, B. Cestnik, and T. Urbancic, “What Can Videolectures.Net and Translectures Do for Opening Higher Education to the Multicultural World,” in Proc. of the 15th Intl. Conf. on Computer Systems and Technologies (CompSysTech’14), Ruse (Bulgaria), 2014, pp. 409-416.
    [Bibtex]
    @inproceedings{Orlic:2014:VTO:2659532.2659649,
     author = {Orlic, Davor and Cestnik, Bojan and Urbancic, Tanja},
     title = {{What Can Videolectures.Net and Translectures Do for Opening Higher Education to the Multicultural World}},
     booktitle = {Proc. of the 15th Intl. Conf. on Computer Systems and Technologies (CompSysTech'14)},
     year = {2014},
     pages = {409--416},
     address = {Ruse (Bulgaria)},
     keywords = {automatic transcription, automatic translation, blended learning, e-learning, information technologies for education, open education, open educational resources},
     pdf= {},
     url = {http://doi.acm.org/10.1145/2659532.2659649},
     doi = {10.1145/2659532.2659649},
    }
  • [PDF] [PDF] A. Pérez-González-de-Martos, J. A. Silvestre-Cerdà, M. Rihtar, A. Juan, and J. Civera, “Using Automatic Speech Transcriptions in Lecture Recommendation Systems,” in Online Proc. of VIII Jornadas en Tecnología del Habla and IV Iberian SLTech Workshop (IberSpeech 2014), Las Palmas de Gran Canaria (Spain), 2014, pp. 149-158.
    [Bibtex]
    @inproceedings{PerSil14,
      booktitle={Online Proc. of VIII Jornadas en Tecnolog\'ia del Habla and IV Iberian SLTech Workshop (IberSpeech 2014)},
      title={{Using Automatic Speech Transcriptions in Lecture Recommendation Systems}},
      author={A. P\'erez-Gonz\'alez-de-Martos and J. A. Silvestre-Cerd\`a and M. Rihtar and A. Juan and J. Civera},
      pages={149--158},
      month=nov,
      year={2014},
      address={Las Palmas de Gran Canaria (Spain)},
      pdf={http://riunet.upv.es/bitstream/handle/10251/54395/IberSPEECH2014_OnlineProceedings-pp149_158-perez_et_al.pdf},
      url={http://hdl.handle.net/10251/54395},
      doi={},
      hdl={http://hdl.handle.net/10251/54395}
    }
  • [PDF] [PDF] S. Piqueras, M. A. del-Agua, A. Giménez, J. Civera, and A. Juan, “Statistical text-to-speech synthesis of Spanish subtitles,” in Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages, Las Palmas de Gran Canaria (Spain), 2014, pp. 40-48.
    [Bibtex]
    @inproceedings{PiqAgu14,
      booktitle={Proc. of IberSpeech 2014: Advances in Speech and Language Technologies for Iberian Languages},
      title={{Statistical text-to-speech synthesis of Spanish subtitles}},
      author={S. Piqueras and M. A. del-Agua and A. Gim\'enez and J. Civera and A. Juan},
      pages={40--48},
      volume={8854},
      series={Lecture Notes in Computer Science},
      month=nov,
      year={2014},
      address={Las Palmas de Gran Canaria (Spain)},
      publisher={Springer International Publishing},
      pdf={http://riunet.upv.es/bitstream/handle/10251/50446/camera_ready.pdf},
      url={http://hdl.handle.net/10251/50446},
      doi={10.1007/978-3-319-13623-3_5},
      hdl={http://hdl.handle.net/10251/50446}
    }
  • [PDF] [PDF] M. Sundermeyer, T. Alkhouli, J. Wuebker, and H. Ney, “Translation Modeling with Bidirectional Recurrent Neural Networks,” in Proc. of the Conf. on Empirical Methods in Natural Language Processing EMNLP 2014, Doha (Qatar), 2014, pp. 14-25.
    [Bibtex]
    @InProceedings{sundermeyer-EtAl:2014:EMNLP2014,
    author={Sundermeyer, Martin and Alkhouli, Tamer and Wuebker, Joern and Ney, Hermann},
    title={{Translation Modeling with Bidirectional Recurrent Neural Networks}},
    booktitle={Proc. of the Conf. on Empirical Methods in Natural Language Processing EMNLP 2014},
    year={2014},
    month=oct,
    pages={14--25},
    address={Doha (Qatar)},
    pdf={https://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=936&row=pdf},
    url={http://aclanthology.info/volumes/proceedings-of-the-2014-conference-on-empirical-methods-in-natural-language-processing-emnlp},
    doi={}
    }
  • [PDF] [PDF] M. Sundermeyer, Z. Tüske, R. Schlüter, and H. Ney, “Lattice Decoding and Rescoring with Long-Span Neural Network Language Models,” in Proc. of Interspeech 2014, Singapore, 2014, pp. 661-665.
    [Bibtex]
    @InProceedings { sundermeyer2014:rescoring,
    author= {Sundermeyer, Martin and T{\"u}ske, Zolt{'a}n and Schl{\"u}ter, Ralf and Ney, Hermann}, 
    title= {{Lattice Decoding and Rescoring with Long-Span Neural Network Language Models}}, 
    booktitle= {Proc. of Interspeech 2014}, 
    year= {2014}, 
    address= {Singapore}, 
    month= sep, 
    pages= {661--665}, 
    pdf = {https://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=955&row=pdf},
    url={http://www.isca-speech.org/archive/interspeech_2014/i14_0661.html},
    doi={}
    }
  • [PDF] [PDF] Z. Tüske, P. Golik, R. Schlüter, and H. Ney, “Acoustic Modeling with Deep Neural Networks Using Raw Time Signal for LVCSR,” in Proc. of Interspeech 2014, Singapore, 2014, pp. 890-894.
    [Bibtex]
    @InProceedings{ tuske2014_is_time,
    author= {T{\"u}ske, Zolt{\'a}n and Golik, Pavel and Schl{\"u}ter, Ralf and Ney, Hermann}, 
    title= {{Acoustic Modeling with Deep Neural Networks Using Raw Time Signal for LVCSR}}, 
    booktitle= {Proc. of Interspeech 2014}, 
    year= {2014}, 
    address= {Singapore}, 
    month= sep, 
    pages= {890--894}, 
    note= {ISCA best student paper award Interspeech 2014},
    pdf = {https://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=937&row=pdf},
    url={http://www.isca-speech.org/archive/interspeech_2014/i14_0890.html},
    doi={}
    }
  • [PDF] [PDF] J. D. Valor Miró, R. N. Spencer, A. Pérez González de Martos, G. Garcés Díaz-Munío, C. Turró, J. Civera, and A. Juan, “Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures,” Open Learning: The Journal of Open, Distance and e-Learning, vol. 29, iss. 1, pp. 72-85, 2014.
    [Bibtex]
    @article{Valor14-OpenLearning,
      author = {Valor Miró, J.D. and Spencer, R.N. and Pérez González de Martos, A. and Garcés Díaz-Munío, G. and Turró, C. and Civera, J. and Juan, A.},
      title = {{Evaluating intelligent interfaces for post-editing automatic transcriptions of online video lectures}},
      journal = {Open Learning: The Journal of Open, Distance and e-Learning},
      volume = {29},
      number = {1},
      pages = {72--85},
      year = {2014},
      pdf={http://riunet.upv.es/bitstream/handle/10251/55925/author_version.pdf},
      url = {http://hdl.handle.net/10251/55925},
      doi = {10.1080/02680513.2014.909722},
      hdl = {http://hdl.handle.net/10251/55925}
    }
  • [PDF] [PDF] J. D. Valor Miró, R. N. Spencer, A. Pérez González de Martos, G. Garcés Díaz-Munío, C. Turró, J. Civera, and A. Juan, “Evaluación del proceso de revisión de transcripciones automáticas para vídeos Polimedia,” in Proc. of I Jornadas de Innovación Educativa y Docencia en Red (IN-RED 2014), València (Spain), 2014, pp. 272-278.
    [Bibtex]
    @INPROCEEDINGS{Valor14-InRed,
      author = {Valor Miró, J.D. and Spencer, R.N. and Pérez González de Martos, A. and Garcés Díaz-Munío, G. and Turró, C. and Civera, J. and Juan, A.},
      booktitle = {Proc. of I Jornadas de Innovación Educativa y Docencia en Red (IN-RED 2014)},
      title = {{Evaluación del proceso de revisión de transcripciones automáticas para vídeos Polimedia}},
      year = {2014},
      month = jul,
      address = {Val\`encia (Spain)},
      pages = {272--278},
      keywords = {ASR; transcripciones; evaluaciones; Docencia en Red; Polimedia},
      pdf={http://riunet.upv.es/bitstream/handle/10251/54397/editor.pdf},
      url={http://hdl.handle.net/10251/54397},
      doi={10.4995/INRED.2014.84},
      hdl={http://hdl.handle.net/10251/54397}
    }
  • [PDF] [PDF] S. Wiesler, K. Irie, Z. Tüske, R. Schlüter, and H. Ney, “The RWTH English lecture recognition system,” in Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2014, Florence (Italy), 2014, pp. 3286-3290.
    [Bibtex]
    @InProceedings { wiesler2014:translectures,
    author= {Wiesler, Simon and Irie, Kazuki and T{\"u}ske, Zolt{\'a}n and Schl{\"u}ter, Ralf and Ney, Hermann},  
    title= {{The RWTH English lecture recognition system}}, 
    booktitle= {Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2014}, 
    year= {2014}, 
    month= may, 
    address= {Florence (Italy)}, 
    pages= {3286--3290}, 
    pdf = {https://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=905&row=pdf},
    url={http://dx.doi.org/10.1109/ICASSP.2014.6854208},
    doi={10.1109/ICASSP.2014.6854208}
    }
  • [PDF] [PDF] S. Wiesler, A. Richard, P. Golik, R. Schlüter, and H. Ney, “RASR/NN: The RWTH neural network toolkit for speech recognition,” in Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2014, Florence (Italy), 2014, pp. 3281-3285.
    [Bibtex]
    @InProceedings { wiesler2014:rasr,
    author= {Wiesler, Simon and Richard, Alexander and Golik, Pavel and Schl{\"u}ter, Ralf and Ney, Hermann}, 
    title= {{RASR/NN: The RWTH neural network toolkit for speech recognition}}, 
    booktitle= {Proc. of IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2014}, 
    year= {2014}, 
    month= may, 
    address= {Florence (Italy)}, 
    pages= {3281--3285}, 
    pdf = {https://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=904&row=pdf},
    url={http://dx.doi.org/10.1109/ICASSP.2014.6854207},
    doi={10.1109/ICASSP.2014.6854207}
    }
  • [PDF] [PDF] J. Wuebker, H. Ney, A. Martínez-Villaronga, A. Giménez, A. Juan, C. Servan, M. Dymetman, and S. Mirkin, “Comparison of Data Selection Techniques for the Translation of Video Lectures,” in Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014), Vancouver (Canada), 2014, pp. 193-207.
    [Bibtex]
    @inproceedings{WueMarSer14,
      booktitle={Proc. of the Eleventh Biennial Conf. of the Association for Machine Translation in the Americas (AMTA-2014)},
      title={{Comparison of Data Selection Techniques for the Translation of Video Lectures}},
      author={Wuebker, Joern and Ney, Hermann and Mart\'inez-Villaronga, Adri\`a and Gim\'enez, Adri\`a and Juan, Alfons and Servan, Christophe and Dymetman, Marc and Mirkin, Shachar},
      pages={193--207},
      month=oct,
      year={2014},
      address={Vancouver (Canada)},
      pdf={https://riunet.upv.es/bitstream/handle/10251/54431/AMTA-2014-Wuebker.pdf},
      url={http://hdl.handle.net/10251/54431},
      doi={},
      hdl={http://hdl.handle.net/10251/54431}
    }

2013

  • [PDF] [PDF] P. Golik, P. Doetsch, and H. Ney, “Cross-Entropy vs. Squared Error Training: a Theoretical and Experimental Comparison,” in Proc. of Interspeech 2013, Lyon (France), 2013, pp. 1756-1760.
    [Bibtex]
    @InProceedings { golik13:criteria,
      author= {Golik, Pavel and Doetsch, Patrick and Ney, Hermann},
      title= {{Cross-Entropy vs. Squared Error Training: a Theoretical and Experimental Comparison}},
      booktitle= {Proc. of Interspeech 2013},
      year= {2013},
      month= aug,
      pages= {1756--1760},
      address= {Lyon (France)},
      pdf= {http://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=861&row=pdf},
      url= {http://www.isca-speech.org/archive/interspeech_2013/i13_1756.html}
    }
  • [PDF] [PDF] P. Golik, Z. Tüske, R. Schlüter, and H. Ney, “Development of the RWTH Transcription System for Slovenian,” in Proc. of Interspeech 2013, Lyon (France), 2013, pp. 3107-3111.
    [Bibtex]
    @InProceedings { golik13:sl,
      author= {Golik, Pavel and T{\"u}ske, Zoltan and Schl{\"u}ter, Ralf and Ney, Hermann},
      title= {{Development of the RWTH Transcription System for Slovenian}},
      booktitle= {Proc. of Interspeech 2013},
      year= {2013},
      month= aug,
      pages= {3107--3111},
      address= {Lyon (France)},
      pdf= {http://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=860&row=pdf},
      url= {http://www.isca-speech.org/archive/interspeech_2013/i13_3107.html}
    }
  • [PDF] [PDF] A. Martínez-Villaronga, M. A. del Agua, J. Andrés-Ferrer, and A. Juan, “Language model adaptation for video lectures transcription,” in Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013, Vancouver (Canada), 2013, pp. 8450-8454.
    [Bibtex]
    @INPROCEEDINGS{Martinez-Villaronga2013,
      author={Mart\'inez-Villaronga, A. and del Agua, M.A. and Andr\'es-Ferrer, J. and Juan, A.},
      booktitle={Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013},
      title={{Language model adaptation for video lectures transcription}},
      year={2013},
      month=may,
      pages={8450--8454},
      address={Vancouver (Canada)},
      issn={1520-6149},
      keywords={language model adaptation; video lectures},
      pdf={http://riunet.upv.es/bitstream/handle/10251/39899/icassp-2013.pdf},
      url={http://hdl.handle.net/10251/39899},
      doi={10.1109/ICASSP.2013.6639314},
      hdl={http://hdl.handle.net/10251/39899}
    }
  • [PDF] [PDF] S. Mirkin and N. Cancedda, “Assessing Quick Update Methods of Statistical Translation Models,” in Proc. of the 10th Intl. Workshop on Spoken Language Translation (IWSLT 2013), Heidelberg (Germany), 2013, pp. 264-271.
    [Bibtex]
    @inproceedings{mirkin13:iwslt,
      author= {Mirkin, Shachar and Cancedda, Nicola},
      title= {{Assessing Quick Update Methods of Statistical Translation Models}},
      booktitle= {Proc. of the 10th Intl. Workshop on Spoken Language Translation (IWSLT 2013)},
      year= {2013},
      month= dec,
      pages= {264--271},
      address= {Heidelberg (Germany)},
      pdf= {http://u.cs.biu.ac.il/~mirkins/publications/Mirkin-cancedda_smt-quick-updates.pdf},
      url= {http://workshop2013.iwslt.org/64.php},
      doi= {}
    }
  • [PDF] [PDF] J. A. Silvestre-Cerdà, A. Pérez, M. Jiménez, C. Turró, A. Juan, and J. Civera, “A System Architecture to Support Cost-Effective Transcription and Translation of Large Video Lecture Repositories,” in Proc. of the IEEE Intl. Conf. on Systems, Man, and Cybernetics SMC 2013, Manchester (UK), 2013, pp. 3994-3999.
    [Bibtex]
    @INPROCEEDINGS{SilvestreCerda2013,
      author={Silvestre-Cerd\`{a}, Joan Albert and P\'{e}rez, Alejandro and Jim\'{e}nez, Manuel and Turr\'{o}, Carlos and Juan, Alfons and Civera, Jorge},
      booktitle={Proc. of the IEEE Intl. Conf. on Systems, Man, and Cybernetics SMC 2013},
      title={{A System Architecture to Support Cost-Effective Transcription and Translation of Large Video Lecture Repositories}},
      year={2013},
      month=oct,
      address={Manchester (UK)},
      pages={3994--3999},
    keywords={Accessibility;Automatic Speech Recognition;Education;Intelligent Interaction;Language Technologies;Machine Translation;Massive Adaptation;Multilingualism;Opencast Matterhorn;Video Lectures},
      pdf={http://riunet.upv.es/bitstream/handle/10251/39896/IEEESMC2013-AuthorVersion.pdf},
      url={http://hdl.handle.net/10251/39896},
      doi={10.1109/SMC.2013.682},
      hdl={http://hdl.handle.net/10251/39896}
    }
  • [PDF] [PDF] M. Sundermeyer, I. Oparin, J. Gauvain, B. Freiberg, R. Schlüter, and H. Ney, “Comparison of feedforward and recurrent neural network language models,” in Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013, Vancouver (Canada), 2013, pp. 8430-8434.
    [Bibtex]
    @INPROCEEDINGS{sundermeyer13:cmp,
      author={Sundermeyer, Martin and Oparin, Ilya and Gauvain, Jean-Luc and Freiberg, Ben and Schl{\"u}ter, Ralf and Ney, Hermann},
      booktitle={Proc. of the IEEE Intl. Conf. on Acoustics, Speech and Signal Processing ICASSP 2013},
      title={Comparison of feedforward and recurrent neural network language models},
      year={2013},
      month=may,
      pages={8430--8434},
      address={Vancouver (Canada)},
      issn={1520-6149},
      keywords={Automatic speech recognition;feedforward neural networks;recurrent neural networks},
      pdf={http://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=843&row=pdf},
      url={http://dx.doi.org/10.1109/ICASSP.2013.6639310},
      doi={10.1109/ICASSP.2013.6639310}
    }
  • [PDF] [PDF] J. Wuebker, S. Peitz, T. Alkhouli, J. Peter, M. Feng, M. Freitag, and H. Ney, “The RWTH Aachen Machine Translation Systems for IWSLT 2013,” in Proc. of the 10th Intl. Workshop on Spoken Language Translation (IWSLT 2013), Heidelberg (Germany), 2013, pp. 88-93.
    [Bibtex]
    @inproceedings{wuebker13:iwslt,
      author= {Wuebker, Joern and Peitz, Stephan and Alkhouli, Tamer and Peter, Jan-Thorsten and Feng, Minwei and Freitag, Markus and Ney, Hermann},
      title= {{The RWTH Aachen Machine Translation Systems for IWSLT 2013}},
      booktitle= {Proc. of the 10th Intl. Workshop on Spoken Language Translation (IWSLT 2013)},
      year= {2013},
      month= dec,
      pages= {88--93},
      address= {Heidelberg (Germany)},
      pdf= {http://www-i6.informatik.rwth-aachen.de/publications/downloader.php?id=897&row=pdf},
      url= {http://workshop2013.iwslt.org/64.php},
      doi= {}
    }

2012

  • [PDF] [PDF] M. del Agua, N. Serrano, J. Civera, and A. Juan, “Character-Based Handwritten Text Recognition of Multilingual Documents,” in Proc. of IberSpeech 2012: Advances in Speech and Language Technologies for Iberian Languages, Madrid (Spain), 2012, pp. 187-196.
    [Bibtex]
    @inproceedings{delAgua12,
      booktitle={Proc. of IberSpeech 2012: Advances in Speech and Language Technologies for Iberian Languages},
      title={{Character-Based Handwritten Text Recognition of Multilingual Documents}},
      author={del Agua, MiguelA. and Serrano, Nicol\'as and Civera, Jorge and Juan, Alfons},
      pages={187--196},
      volume={328},
      series={Communications in Computer and Information Science},
      year={2012},
      address={Madrid (Spain)},
      publisher={Springer Berlin Heidelberg},
      pdf={http://riunet.upv.es/bitstream/handle/10251/35180/iberspeech2012-CAMREADY.pdf},
      url={http://hdl.handle.net/10251/35180},
      doi={10.1007/978-3-642-35292-8_20},
      hdl={http://hdl.handle.net/10251/35180}
    }
  • [PDF] [PDF] G. Gascó, M. Rocha, G. Sanchis-Trilles, J. Andrés-Ferrer, and F. Casacuberta, “Does more data always yield better translations?,” in Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012), Avignon (France), 2012, pp. 152-161.
    [Bibtex]
    @InProceedings{gasco-EtAl:2012:EACL2012,
      author    = {Gasc\'{o}, Guillem  and  Rocha, Martha-Alicia  and  Sanchis-Trilles, Germ\'{a}n  and  Andr\'{e}s-Ferrer, Jes\'{u}s  and  Casacuberta, Francisco},
      title     = {{Does more data always yield better translations?}},
      booktitle = {Proc. of the 13th Conf. of the European Chapter of the Association for Computational Linguistics (EACL 2012)},
      month     = apr,
      year      = {2012},
      address   = {Avignon (France)},
      publisher = {Association for Computational Linguistics},
      pages     = {152--161},
      pdf       = {http://www.aclweb.org/anthology/E12-1016},
      url       = {http://hdl.handle.net/10251/35214},
      doi       = {},
      hdl       = {http://hdl.handle.net/10251/35214}
    }
  • [PDF] [PDF] J. A. Silvestre-Cerdà, M. A. del-Agua, G. Garcés, G. Gascó, A. Giménez, A. Martínez, A. Pérez, I. Sánchez, N. Serrano, R. Spencer, J. D. Valor, J. Andrés-Ferrer, J. Civera, A. Sanchis, and A. Juan, “transLectures,” in Online Proc. of VII Jornadas en Tecnología del Habla and III Iberian SLTech Workshop (IberSpeech 2012), Madrid (Spain), 2012, pp. 345-351.
    [Bibtex]
    @inproceedings{translectures12,
      booktitle={Online Proc. of VII Jornadas en Tecnolog\'ia del Habla and III Iberian SLTech Workshop (IberSpeech 2012)},
      title={{transLectures}},
      author={J. A. Silvestre-Cerd\`a and M. A. del-Agua and G. Garc\'es and G. Gasc\'o and A. Gim\'enez and A. Mart\'inez and A. P\'erez and I. S\'anchez and N. Serrano and R. Spencer and J. D. Valor and J. Andr\'es-Ferrer and J. Civera and A. Sanchis and A. Juan},
      pages={345--351},
      month=nov,
      year={2012},
      address={Madrid (Spain)},
      pdf={http://riunet.upv.es/bitstream/handle/10251/37290/1209IberSpeech.pdf},
      url={http://hdl.handle.net/10251/37290},
      doi={},
      hdl={http://hdl.handle.net/10251/37290}
    }
  • [PDF] [PDF] J. A. Silvestre-Cerdà, J. Andrés-Ferrer, and J. Civera, “Explicit length modelling for statistical machine translation,” Pattern Recognition, vol. 45, iss. 9, pp. 3183-3192, 2012.
    [Bibtex]
    @article{SilvestreCerda20123183,
      title = {{Explicit length modelling for statistical machine translation}},
      journal = {Pattern Recognition},
      volume = {45},
      number = {9},
      pages = {3183--3192},
      year = {2012},
      note = {Best Papers of Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA'2011)},
      issn = {0031-3203},
      author = {Silvestre-Cerd\`{a}, Joan Albert and Andr\'{e}s-Ferrer, Jes\'{u}s and Civera, Jorge},
      keywords = {Length modelling},
      keywords = {Log-linear models},
      keywords = {Phrase-based models},
      keywords = {Statistical machine translation},
      pdf = {http://riunet.upv.es/bitstream/handle/10251/34996/PR-D-11-00647R1.pdf},
      url = {http://hdl.handle.net/10251/34996},
      doi = {10.1016/j.patcog.2012.01.006},
      hdl = {http://hdl.handle.net/10251/34996}
    }
  • [PDF] [PDF] J. Valor, A. Pérez, J. Civera, and A. Juan, “Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform,” in Proc. of IberSpeech 2012: Advances in Speech and Language Technologies for Iberian Languages, Madrid (Spain), 2012, pp. 237-246.
    [Bibtex]
    @inproceedings{Valor12,
      booktitle={Proc. of IberSpeech 2012: Advances in Speech and Language Technologies for Iberian Languages},
      title={{Integrating a State-of-the-Art ASR System into the Opencast Matterhorn Platform}},
      author={Valor, JuanDaniel and P\'erez, Alejandro and Civera, Jorge and Juan, Alfons},
      pages={237--246},
      volume={328},
      series={Communications in Computer and Information Science},
      year={2012},
      address={Madrid (Spain)},
      publisher={Springer Berlin Heidelberg},
      keywords={Speech Recognition; Linear Combination; Language Modeling; Google N-Gram; Opencast Matterhorn},
      pdf={http://riunet.upv.es/bitstream/handle/10251/35190/paper.pdf},
      url={http://hdl.handle.net/10251/35190},
      doi={10.1007/978-3-642-35292-8_25},
      hdl={http://hdl.handle.net/10251/35190}
    }