Spectral estimation using a log-distance error criterion applied to speech recognition
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 258-261 vol.1
- https://doi.org/10.1109/icassp.1989.266414
Abstract
A novel algorithm is presented for the estimation of a signal in noise. The distortion criterion used is based on the distance between log spectra. In many signal-processing applications, such as speech recognition, log spectra are much closer to the parameters used in a discriminator than power spectra. Therefore, it is believed that this spectral estimation technique should lead to better results than previously developed techniques such as spectral subtraction. The present technique performed better than spectral subtraction in noise immunity experiments on the IBM isolated word speech-recognition system, although at the expense of additional computational requirements.Keywords
This publication has 5 references indexed in Scilit:
- A real-time, isolated-word, speech recognition system for dictation transcriptionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Noise adaptation in a hidden Markov model speech recognition systemComputer Speech & Language, 1989
- Speech enhancement using a minimum mean-square error log-spectral amplitude estimatorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1985
- Speech enhancement using a soft-decision noise suppression filterIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- Suppression of acoustic noise in speech using spectral subtractionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1979