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

Improving ASR Performance for Reverberant Speech

Brian E. D. Kingsbury, Nelson Morgan, Steven Greenberg

International Computer Science Institute, Berkeley, CA, USA

The performance of current automatic speech recognition (ASR) systems is very sensitive to the presence of room reverberation in the incoming speech signal. We investigate a family of front-end speech representations that focus on slow changes in the the gross spectral structure of speech for their ability to improve the robustness of ASR systems to reverberation. A number of the front ends provide a statistically significant improvement in performance over established front ends such as PLP; however, the performance of ASR systems on highly reverberant speech is still disappointing when compared with the performance of human listeners.

Full Paper

Bibliographic reference.  Kingsbury, Brian E. D. / Morgan, Nelson / Greenberg, Steven (1997): "Improving ASR performance for reverberant speech", In RSR-1997, 87-90.