%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}, }