%Aigaion2 BibTeX export from Idiap Publications
%Saturday 21 December 2024 07:55:53 PM

@INPROCEEDINGS{misr04,
         author = {Misra, Hemant and Ikbal, Shajith and Bourlard, Herv{\'{e}} and Hermansky, Hynek},
       projects = {Idiap},
          month = {5},
          title = {Spectral Entropy Based Feature for Robust {ASR}},
      booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
           year = {2004},
        address = {Montreal, Canada},
           note = {IDIAP-RR 2003 56},
       crossref = {misra-rr-03-56},
       abstract = {In general, entropy gives us a measure of the number of bits required to represent some information. When applied to probability mass function (PMF,',','),
 entropy can also be used to measure the ``peakiness'' of a distribution. In this paper, we propose using the entropy of short time Fourier transform spectrum, normalised as PMF, as an additional feature for automatic speech recognition (ASR). It is indeed expected that a peaky spectrum, representation of clear formant structure in the case of voiced sounds, will have low entropy, while a flatter spectrum corresponding to non-speech or noisy regions will have higher entropy. Extending this reasoning further, we introduce the idea of multi-band/multi-resolution entropy feature where we divide the spectrum into equal size sub-bands and compute entropy in each sub-band. The results presented in this paper show that multi-band entropy features used in conjunction with normal cepstral features improve the performance of ASR system.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-56.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-56.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{misra-rr-03-56,
         author = {Misra, Hemant and Ikbal, Shajith and Bourlard, Herv{\'{e}} and Hermansky, Hynek},
       projects = {Idiap},
          title = {Spectral Entropy Based Feature for Robust {ASR}},
           type = {Idiap-RR},
         number = {Idiap-RR-56-2003},
           year = {2003},
    institution = {IDIAP},
        address = {Martigny, Switzerland},
           note = {in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing {(ICASSP)}, 2004},
       abstract = {In general, entropy gives us a measure of the number of bits required to represent some information. When applied to probability mass function (PMF,',','),
 entropy can also be used to measure the ``peakiness'' of a distribution. In this paper, we propose using the entropy of short time Fourier transform spectrum, normalised as PMF, as an additional feature for automatic speech recognition (ASR). It is indeed expected that a peaky spectrum, representation of clear formant structure in the case of voiced sounds, will have low entropy, while a flatter spectrum corresponding to non-speech or noisy regions will have higher entropy. Extending this reasoning further, we introduce the idea of multi-band/multi-resolution entropy feature where we divide the spectrum into equal size sub-bands and compute entropy in each sub-band. The results presented in this paper show that multi-band entropy features used in conjunction with normal cepstral features improve the performance of ASR system.},
            pdf = {https://publications.idiap.ch/attachments/reports/2003/rr03-56.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2003/rr03-56.ps.gz},
ipdinar={2003},
ipdmembership={speech},
language={English},
}