A Comparative Analysis of Channel-Robust Features and Channel Equalization Methods for Speech Recognition

Vaseghi, S. and Milner, B. P. (1996) A Comparative Analysis of Channel-Robust Features and Channel Equalization Methods for Speech Recognition. In: 4th International Conference on Spoken Language, 1996-10-03 - 1996-10-06.

Full text not available from this repository. (Request a copy)

Abstract

The use of a speech recognition system with telephone channel environments, or different microphones, requires channel equalisation. In speech recognition, the speech models provide 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 is to use a set of features which is more robust to channel distortion. Channel distortions result in an amplitude-tilt of the speech cepstrum, and so differential cepstral features should 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. They present results demonstrating that a major advantage of cepstral-time matrices is their channel insensitive character.

Item Type:	Conference or Workshop Item (Other)
Faculty \ School:	Faculty of Science > School of Computing Sciences
Depositing User:	EPrints Services
Date Deposited:	01 Oct 2010 13:41
Last Modified:	15 Dec 2022 01:08
URI:	https://ueaeprints.uea.ac.uk/id/eprint/2988
DOI:	10.1109/ICSLP.1996.607741

Actions (login required)

View Item