%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 08:58:43 AM

@INPROCEEDINGS{Duffner_ICSAP_2011,
         author = {Duffner, Stefan and Motlicek, Petr and Korchagin, Danil},
       projects = {Idiap, TA2},
          month = {2},
          title = {The TA2 Database - A Multi-Modal Database from Home Entertainment},
      booktitle = {International Conference on Signal Acquisition and Processing},
           year = {2011},
       location = {Singapore},
       crossref = {Duffner_Idiap-RR-37-2010},
       abstract = {This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating and playing online games with each other. Extensive annotation of head positions, voice activity and word transcription has been performed on the dataset, making it especially useful for evaluating
automatic speech-recognition, voice activity detection, speaker localisation, multi-face detection and tracking, and other audio-visual analysis algorithms.},
            pdf = {https://publications.idiap.ch/attachments/papers/2010/Duffner_ICSAP_2011.pdf}
}



crossreferenced publications: 
@TECHREPORT{Duffner_Idiap-RR-37-2010,
         author = {Duffner, Stefan and Motlicek, Petr and Korchagin, Danil},
       projects = {Idiap},
          month = {10},
          title = {The TA2 Database - A Multi-Modal Database from Home Entertainment},
           type = {Idiap-RR},
         number = {Idiap-RR-37-2010},
           year = {2010},
    institution = {Idiap},
        address = {Rue Marconi 19, CH-1920 Martigny},
       abstract = {This paper presents a new database containing high-definition audio and video recordings in a rather unconstrained video-conferencing-like environment. The database consists of recordings of people sitting around a table in two separate rooms communicating and playing online games with each other. Extensive annotation of head positions, voice activity and word transcription has been performed on the dataset, making it especially useful for evaluating automatic speech-recognition, voice activity detection, speaker localisation, multi-face detection and tracking, and other audio-visual analysis algorithms.},
            pdf = {https://publications.idiap.ch/attachments/reports/2011/Duffner_Idiap-RR-37-2010.pdf}
}