Bayesian channel equalisation and robust features for speech recognition
Authors:
- B.P. MilnerBMB.P. Milner
- S.V. VaseghiSVS.V. Vaseghi
- 1 January 1996
- journal article
- Published by Institution of Engineering and Technology (IET) in IEE Proceedings - Vision, Image, and Signal Processing
- Vol. 143 (4) , 223
Abstract
The use of a speech recognition system with telephone channel environments, or different microphones, requires channel equalisation. In speech recognition, the speech model provides a bank of statistical information that can be used in the channel identification and equalisation process. The authors consider HMM-based channel equalisation, and present results demonstrating that substantial improvement can be obtained through the equalisation process. An alternative method, for speech recognition, is to use a feature set which is more robust to channel distortion. Channel distortions result in an amplitude tilt of the speech cepstrum, and therefore differential cepstral features provide a measure of immunity to channel distortions. In particular the cepstral-time feature matrix, in addition to providing a framework for representing speech dynamics, can be made robust to channel distortions. The authors present results demonstrating that a major advantage of cepstral-time matrices is their channel insensitive characteKeywords
This publication has 4 references indexed in Scilit:
- Advanced Signal Processing and Digital Noise Reduction1996
- Tutorial on higher-order statistics (spectra) in signal processing and system theory: theoretical results and some applicationsProceedings of the IEEE, 1991
- Adaptive equalizationProceedings of the IEEE, 1985
- Techniques for Adaptive Equalization of Digital Communication SystemsBell System Technical Journal, 1966