Neural net classifiers for robust speech recognition under noisy environments
Kuldip K. Paliwal · International Conference on Acoustics, Speech, and Signal Processing · 2002
The multilayer perceptron (MLP) classifier is studied for the recognition of noisy speech, and its performance is compared with that of conventional pattern classifiers such as the maximum-likelihood (ML) classifier and the k-nearest-neighbor (kNN) classifier. The linear prediction (LP) parameters derived through tenth-order LP analysis are used as the recognition parameters. Different LP parametric representations are compared as to their recognition performance with the MLP classifier, and the cepstral coefficient representation is found to be the best parametric representation. When ten cepstral coefficients are used as recognition parameters, the performance of the MLP classifier is found to be significantly better than that of the ML and the kNN classifiers for noisy speech. Use of 15 cepstral coefficients (obtained by extrapolating the ten cepstral coefficients) improves the recognition performance of the MLP classifier for noisy speech further.>