%Aigaion2 BibTeX export from Idiap Publications
%Thursday 26 December 2024 04:05:00 PM

@TECHREPORT{hari-rr-06-29,
         author = {Maganti, Hari Krishna and Gatica-Perez, Daniel},
       projects = {Idiap},
          title = {{Speaker Localization for Microphone Array-Based ASR: The Effects of Accuracy on Overlapping Speech}},
           type = {Idiap-RR},
         number = {Idiap-RR-29-2006},
           year = {2006},
    institution = {IDIAP},
        address = {Martigny, Switzerland},
       abstract = {Accurate speaker location is essential for optimal performance of distant speech acquisition systems using microphone array techniques. However, to the best of our knowledge, no comprehensive studies on the degradation of automatic speech recognition (ASR) as a function of speaker location accuracy in a multi-party scenario exist. In this paper, we describe a framework for evaluation of the effects of speaker location errors on a microphone array-based ASR system, in the context of meetings in multi-sensor rooms comprising multiple cameras and microphones. Speakers are manually annotated in videos in different camera views, and triangulation is used to determine an accurate speaker location. Errors in the speaker location are then induced in a systematic manner to observe their influence on speech recognition performance. The system is evaluated on real overlapping speech data collected with simultaneous speakers in a meeting room. The results are compared with those obtained from close-talking headset microphones, lapel microphones, and speaker location based on audio-only and audio-visual information approaches.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/rr06-29.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/rr06-29.ps.gz},
ipdinar={2006},
ipdmembership={speech},
language={English},
}