Recognition of noisy speech using cumulant-based linear prediction analysis
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 429-432 vol.1
- https://doi.org/10.1109/icassp.1991.150368
Abstract
The use of cumulant-based LP (linear prediction) analysis for speech recognition in the presence of noise is proposed. This method assumes the speech signal to be non-Gaussian. It is shown that cepstral coefficients derived by this method are quite insensitive to additive Gaussian noise which can be white or colored. The performance of a recognizer based on these estimates is compared to the performance of one that uses LP estimates derived from the autocorrelation function. It is found that at low SNR (below about 20 dB) the cumulant-based estimates outperform the autocorrelation-based estimates. At higher SNRs the reverse is true. The reasons for this behavior are not yet understood. However, it is shown that, by combining the two estimates, one can achieve recognition accuracy that is better than that of the conventional recognizer at all SNRs.Keywords
This publication has 12 references indexed in Scilit:
- A linear predictive front-end processor for speech recognition in noisy environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- On the use of bandpass liftering in speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Robustness against noise: The role of timing-synchrony measurementPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Neural net classifiers for robust speech recognition under noisy environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The short-time modified coherence representation and noisy speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Identification of nonminimum phase systems using higher order statisticsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- A family of distortion measures based upon projection operation for robust speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989
- A frequency-weighted Itakura spectral distortion measure and its application to speech recognition in noiseIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988
- Bispectrum estimation: A digital signal processing frameworkProceedings of the IEEE, 1987