%Aigaion2 BibTeX export from Idiap Publications
%Tuesday 03 December 2024 05:34:02 PM

@INPROCEEDINGS{dines:interspeech-icslp:2006,
         author = {Dines, John and Vepa, Jithendra and Hain, Thomas},
       projects = {Idiap},
          title = {The segmentation of multi-channel meeting recordings for automatic speech recognition},
      booktitle = {Int. Conf. on Spoken Language Processing ({Interspeech ICSLP})},
           year = {2006},
        address = {Pittsburgh, USA},
           note = {IDIAP-RR 06-22},
       crossref = {dines:rr06-22},
       abstract = {One major research challenge in the domain of the analysis of meeting room data is the automatic transcription of what is spoken during meetings, a task which has gained considerable attention within the ASR research community through the NIST rich transcription evaluations conducted over the last three years. One of the major difficulties in carrying out automatic speech recognition (ASR) on this data is dealing with the challenging recording environment, which has instigated the development of novel audio pre-processing approaches. In this paper we present a system for the automatic segmentation of multiple-channel individual headset microphone (IHM) meeting recordings for automatic speech recognition. The system relies on an MLP classifier trained from several meeting room corpora to identify speech/non-speech segments of the recordings. We give a detailed analysis of the segmentation performance for a number of system configurations, with our best system achieving ASR performance on automatically generated segments within 1.3\\% (3.7\\% relative) of a manual segmentation of the data.},
            pdf = {https://publications.idiap.ch/attachments/papers/2006/dines-interspeech-icslp-2006.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2006/dines-interspeech-icslp-2006.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{dines:rr06-22,
         author = {Dines, John and Vepa, Jithendra and Hain, Thomas},
       projects = {Idiap},
          title = {The segmentation of multi-channel meeting recordings for automatic speech recognition},
           type = {Idiap-RR},
         number = {Idiap-RR-22-2006},
           year = {2006},
    institution = {IDIAP},
           note = {Published in Interspeech-ICSLP 2006, Pittsburgh},
       abstract = {One major research challenge in the domain of the analysis of meeting room data is the automatic transcription of what is spoken during meetings, a task which has gained considerable attention within the ASR research community through the NIST rich transcription evaluations conducted over the last three years. One of the major difficulties in carrying out automatic speech recognition (ASR) on this data is dealing with the challenging recording environment, which has instigated the development of novel audio pre-processing approaches. In this paper we present a system for the automatic segmentation of multiple-channel individual headset microphone (IHM) meeting recordings for automatic speech recognition. The system relies on an MLP classifier trained from several meeting room corpora to identify speech/non-speech segments of the recordings. We give a detailed analysis of the segmentation performance for a number of system configurations, with our best system achieving ASR performance on automatically generated segments within 1.3\\% (3.7\\% relative) of a manual segmentation of the data.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/dines-idiap-rr-06-22.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/dines-idiap-rr-06-22.ps.gz},
ipdmembership={speech},
}