The use of wavelet transforms in phoneme recognition

Abstract

This study investigates the usefulness of wavelet transforms in phoneme recognition. Both discrete wavelet transforms (DWT) and sampled continuous wavelet transforms (SCWT) are tested. The wavelet transform is used as a part of the front-end processor which extracts feature vectors for a speakerindependent HMM-based phoneme recognizer. The results are evaluated on a portion of TIMIT corpus consisting of 30293 phoneme tokens for training and 14489 phoneme tokens for testing. The test results suggest that SCWT gives considerably better recognition rate than DWT. On the other hand, the improvement of SCWT over Mel-scale cepstral coecients appears to be marginal.

Modified Discrete Wavelet Features for Phoneme Recognition

“…Recently, the Discrete Wavelet Transform (DWT) has been used for feature extraction [3]. [4], [5], [6], [7].…”

“…This is because DWT can be effectively used to separate out short impulses from a low frequency background easily by using its multi-resolution capability. This property of DWT has been exploited in phoneme recognition by using the high-energy wavelet coefficients as features [3], [4], [5]. However, the DWT suffers from two problems.…”