Acoustical pre-processing for robust speech recognition
HLT '89 Proceedings of the workshop on Speech and Natural Language
Spectral estimation for noise robust speech recognition
HLT '89 Proceedings of the workshop on Speech and Natural Language
HLT '91 Proceedings of the workshop on Speech and Natural Language
RASTA-PLP speech analysis technique
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
| Hi-index | 0.00 |
In this paper we discuss recent results from our efforts to make SPHINX, the CMU continuous-speech speaker-independent recognition system, robust to changes in the environment. To deal with differences in noise level and spectral tilt between close-talking and desk-top microphones, we describe two novel methods based on additive corrections in the cepstral domain. In the first algorithm, an additive correction is imposed that depends on the instantaneous SNR of the signal. In the second technique, EM techniques are used to best match the cepstral vectors of the input utterances to the ensemble of codebook entries representing a standard acoustical ambience. Use of these algorithms dramatically improves recognition accuracy when the system is tested on a microphone other than the one on which it was trained.