4th International Conference on Spoken Language Processing
Philadelphia, PA, USA
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. in this paper we consider HMM-based channel equalistaion, 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. We present results demonstrating that a major advantage of cepstral-time matrices is their channel insensitive character.
Bibliographic reference. Vaseghi, Saeed V. / Milner, Ben (1996): "A comparitive analysis of channel-robust features and channel equalization methods for speech recognition", In ICSLP-1996, 877-880.