%Aigaion2 BibTeX export from Idiap Publications
%Sunday 22 December 2024 04:26:04 AM

@INPROCEEDINGS{ajmera-rr-03-39b,
         author = {Ajmera, Jitendra and McCowan, Iain A. and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {An Online Audio Indexing System},
        journal = {Internation Conference on Spoken Language Processing (ICSLP)},
           year = {2004},
           note = {IDIAP RR 03-39},
       crossref = {ajmera-rr-03-39},
       abstract = {This paper presents overview of an online audio indexing system, which creates a searchable index of speech content embedded in digitized audio files. This system is based on our recently proposed offline audio segmentation techniques. As the data arrives continuously, the system first finds boundaries of the acoustically homogenous segments. Next, each of these segments is classified as speech, music or {\it mixture} classes, where mixtures are defined as regions where speech and other non-speech sounds are present simultaneously and noticeably. The speech segments are then clustered together to provide consistent speaker labels. The speech and mixture segments are converted to text via an ASR system. The resulting words are time-stamped together with other metadata information (speaker identity, speech confidence score) in an XML file to rapidly identify and access target segments. In this paper, we analyze the performance at each stage of this audio indexing system and also compare it with the performance of the corresponding offline modules.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-39b.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-39b.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{ajmera-rr-03-39,
         author = {Ajmera, Jitendra and McCowan, Iain A. and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {An Online Audio Indexing System},
           type = {Idiap-RR},
         number = {Idiap-RR-39-2003},
           year = {2003},
    institution = {IDIAP},
           note = {Accepted for publication in ICSLP 2004},
       abstract = {This paper presents overview of an online audio indexing system, which creates a searchable index of speech content embedded in digitized audio files. This system is based on our recently proposed offline audio segmentation techniques. As the data arrives continuously, the system first finds boundaries of the acoustically homogenous segments. Next, each of these segments is classified as speech, music or {\it mixture} classes, where mixtures are defined as regions where speech and other non-speech sounds are present simultaneously and noticeably. The speech segments are then clustered together to provide consistent speaker labels. The speech and mixture segments are converted to text via an ASR system. The resulting words are time-stamped together with other metadata information (speaker identity, speech confidence score) in an XML file to rapidly identify and access target segments. In this paper, we analyze the performance at each stage of this audio indexing system and also compare it with the performance of the corresponding offline modules.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-39.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-39.ps.gz},
ipdmembership={speech},
}