%Aigaion2 BibTeX export from Idiap Publications
%Thursday 26 December 2024 01:03:46 PM

@TECHREPORT{Taghizadeh_Idiap-RR-16-2011,
         author = {Taghizadeh, Mohammad J. and Garner, Philip N. and Bourlard, Herv{\'{e}} and Abutalebi, Hamid Reza and Asaei, Afsaneh},
       projects = {Idiap, IM2},
          month = {6},
          title = {AN INTEGRATED FRAMEWORK FOR MULTI-CHANNEL MULTI-SOURCE LOCALIZATION AND VOICE ACTIVITY DETECTION},
           type = {Idiap-RR},
      booktitle = {IEEE Workshop on Hands-free Speech Communication and Microphone Arrays},
         number = {Idiap-RR-16-2011},
           year = {2011},
       location = {30 May – 1 June 2011, Edinburgh, Scotland},
    institution = {Idiap},
       abstract = {Two of the major challenges in microphone array based adap-
tive beamforming, speech enhancement and distant speech
recognition, are robust and accurate source localization and
voice activity detection. This paper introduces a spatial gra-
dient steered response power using the phase transform (SRP-
PHAT) method which is capable of localization of competing
speakers in overlapping conditions. We further investigate the
behavior of the SRP function and characterize theoretically a
fixed point in its search space for the diffuse noise field. We
call this fixed point the null position in the SRP search space.
Building on this evidence, we propose a technique for multi-
channel voice activity detection (MVAD) based on detection
of a maximum power corresponding to the null position. The
gradient SRP-PHAT in tandem with the MVAD form an inte-
grated framework of multi-source localization and voice ac-
tivity detection. The experiments carried out on real data
recordings show that this framework is very effective in prac-
tical applications of hands-free communication.},
            pdf = {https://publications.idiap.ch/attachments/reports/2011/Taghizadeh_Idiap-RR-16-2011.pdf}
}