%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 04:49:14 PM

@INPROCEEDINGS{li:Interspeech:2007,
         author = {Li, Weifeng and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {Non-linear Spectral Contrast Stretching for In-car Speech Recognition},
      booktitle = {Interspeech-Eurospeech # to appear in html},
           year = {2007},
           note = {IDIAP-RR 07-53},
       crossref = {li:rr07-53},
       abstract = {In this paper, we present a novel feature normalization method in the log-scaled spectral domain for improving the noise robustness of speech recognition front-ends. In the proposed scheme, a non-linear contrast stretching is added to the outputs of log mel-filterbanks (MFB) to imitate the adaptation of the auditory system under adverse conditions. This is followed by a two-dimensional filter to smooth out the processing artifacts. The proposed MFCC front-ends perform remarkably well on CENSREC-2 in-car database with an average relative improvement of 29.3\\% compared to baseline MFCC system. It is also confirmed that the proposed processing in log MFB domain can be integrated with conventional cepstral post-processing techniques to yield further improvements. The proposed algorithm is simple and requires only a small extra computation load.},
            pdf = {https://publications.idiap.ch/attachments/papers/2007/li-Interspeech-2007.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2007/li-Interspeech-2007.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{li:rr07-53,
         author = {Li, Weifeng and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {Non-linear Spectral Contrast Stretching for In-car Speech Recognition},
           type = {Idiap-RR},
         number = {Idiap-RR-53-2007},
           year = {2007},
    institution = {IDIAP},
       abstract = {In this paper, we present a novel feature normalization method in the log-scaled spectral domain for improving the noise robustness of speech recognition front-ends. In the proposed scheme, a non-linear contrast stretching is added to the outputs of log mel-filterbanks (MFB) to imitate the adaptation of the auditory system under adverse conditions. This is followed by a two-dimensional filter to smooth out the processing artifacts. The proposed MFCC front-ends perform remarkably well on CENSREC-2 in-car database with an average relative improvement of 29.3\\% compared to baseline MFCC system. It is also confirmed that the proposed processing in log MFB domain can be integrated with conventional cepstral post-processing techniques to yield further improvements. The proposed algorithm is simple and requires only a small extra computation load.},
            pdf = {https://publications.idiap.ch/attachments/reports/2007/li-idiap-rr-07-53.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2007/li-idiap-rr-07-53.ps.gz},
ipdmembership={speech},
}