Gaussian Mixture Model based Mutual Information Estimation between Frequency Bands in Speech
2002 (English)In: 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, 525-528 p.Conference paper (Refereed)
In this paper, we investigate the dependency between the spectral envelopes of speech in disjoint frequency bands, one covering the telephone bandwidth from 0.3 kHz to 3.4 kHz and one covering the frequencies from 3.7 kHz to 8 kHz. The spectral envelopes are jointly modeled with a Gaussian mixture model based on mel-frequency cepstral coefficients and the log-energy-ratio of the disjoint frequency bands. Using this model, we quantify the dependency between bands through their mutual information and the perceived entropy of the high frequency band. Our results indicate that the mutual information is only a small fraction of the perceived entropy of the high band. This suggests that speech bandwidth extension should not rely only on mutual information between narrow- and high-band spectra. Rather, such methods need to make use of perceptual properties to ensure that the extended signal sounds pleasant.
Place, publisher, year, edition, pages
2002. 525-528 p.
, International Conference on Acoustics Speech and Signal Processing (ICASSP), ISSN 1520-6149
Bandwidth, Estimation, Mathematical models, Speech intelligibility, Speech transmission
Fluid Mechanics and Acoustics
IdentifiersURN: urn:nbn:se:kth:diva-5789ISI: 000177510400132ISBN: 0-7803-7402-9OAI: oai:DiVA.org:kth-5789DiVA: diva2:10284
IEEE International Conference on Acoustics, Speech, and Signal Processing ORLANDO, FL, MAY 13-17, 2002
QC 201009142006-05-232006-05-232010-09-14Bibliographically approved