Robust Speech Recognition for Unknown Communication Channels Pont-à-Mousson, France April 17-18, 1997

Automatic Speech Recognition for Time-Varying Channels

Keith M. Pouting

Speech Research Unit, DERA Malvern, Great Malvern, Worcs., UK

Any mismatch between training and test conditions can cause difficulty for current automatic speech recognition systems. This paper presents a simple tracking algorithm to compensate for changing transmission channel characteristics during recognition. The algorithm is designed to work in the context of a continuous single-pass speech recognition system and to be robust to speech recognition errors. Experiments show that it can successfully compensate for mismatched microphones and microphone positions.

Full Paper

Bibliographic reference.  Pouting, Keith M. (1997): "Automatic speech recognition for time-varying channels", In RSR-1997, 175-180.