%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 06:26:43 PM

@ARTICLE{Kumatani_ASLP_2009,
         author = {Kumatani, Kenichi and McDonough, John and Rauch, Barbara and Klakow, Dietrich and Garner, Philip N. and Li, Weifeng},
       projects = {AMIDA},
          month = {7},
          title = {Beamforming with a Maximum Negentropy Criterion},
        journal = {IEEE Transactions on Audio Speech and Language Processing},
         volume = {17},
         number = {5},
           year = {2009},
       crossref = {kumatani:rr08-29},
       abstract = {In this paper, we address a beamforming application
based on the capture of far-field speech data from a single
speaker in a real meeting room. After the position of the
speaker is estimated by a speaker tracking system, we construct
a subband-domain beamformer in generalized sidelobe canceller
(GSC) configuration. In contrast to conventional practice, we then
optimize the active weight vectors of the GSC so as to obtain an
output signal with maximum negentropy (MN). This implies the
beamformer output should be as non-Gaussian as possible. For
calculating negentropy, we consider the {\^{I}}“ and the generalized
Gaussian (GG) pdfs. After MN beamforming, Zelinski post-
filtering is performed to further enhance the speech by remov-
ing residual noise. Our beamforming algorithm can suppress
noise and reverberation without the signal cancellation problems
encountered in the conventional beamforming algorithms. We
demonstrate this fact through a set of acoustic simulations. More-
over, we show the effectiveness of our proposed technique through
a series of far-field automatic speech recognition experiments on
the Multi-Channel Wall Street Journal Audio Visual Corpus (MC-
WSJ-AV,',','),
 a corpus of data captured with real far-field sensors, in
a realistic acoustic environment, and spoken by real speakers. On
the MC-WSJ-AV evaluation data, the delay-and-sum beamformer
with post-filtering achieved a word error rate (WER) of 16.5\%.
MN beamforming with the {\^{I}}“ pdf achieved a 15.8\% WER, which
was further reduced to 13.2\% with the GG pdf, whereas the
simple delay-and-sum beamformer provided a WER of 17.8\%.
To the best of our knowledge, no lower error rates at present
have been reported in the literature on this ASR task.},
            pdf = {https://publications.idiap.ch/attachments/papers/2008/Kumatani_ASLP_2009.pdf}
}



crossreferenced publications: 
@TECHREPORT{kumatani:rr08-29,
         author = {Kumatani, Kenichi and McDonough, John and Rauch, Barbara and Garner, Philip N. and Li, Weifeng and Dines, John},
       projects = {Idiap},
          title = {Adaptive Beamforming with a Maximum Negentropy Criterion},
           type = {Idiap-RR},
         number = {Idiap-RR-29-2008},
           year = {2008},
    institution = {IDIAP},
       abstract = {This paper presents an adaptive beamforming application based on the capture of far-field speech data from a real single speaker in a real meeting room. After the position of a speaker is estimated by a speaker tracking system, we construct a subband-domain beamformer in generalized sidelobe canceller (GSC) configuration. In contrast to conventional practice, we then optimize the active weight vectors of the GSC so that the distribution of an output signal is as non-Gaussian as possible. We consider kurtosis in order to measure the degree of non-Gaussianity. Our beamforming algorithms can suppress noise and reverberation without the signal cancellation problems encountered in conventional beamforming algorithms. We demonstrate the effectiveness of our proposed techniques through a series of far-field automatic speech recognition experiments on the Multi-Channel Wall Street Journal Audio Visual Corpus (MC-WSJ-AV). The beamforming algorithm proposed here achieved a 13.6\\% WER, whereas the simple delay-and-sum beamformer provided a WER of 17.8\\%.},
            pdf = {https://publications.idiap.ch/attachments/reports/2008/kumatani-idiap-rr-08-29.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2008/kumatani-idiap-rr-08-29.ps.gz},
ipdmembership={speech},
}