Robust feature extracting of speech signal based on wavelet packet transform

This paper proposed a novel feature extraction algorithm aiming at improving speech recognition robustness in noise environmental conditions. Different frequency within corresponding critical bandwidth signal for human ear cause basement membrane vibration in different location, while the constant Q characteristics of each analysis frequency for wavelet packet transform and signal processing characteristics for human auditory are consistent, so this paper combined with the frequency band multi-level division with wavelet packet transform, and according to the characteristics for human ear perception frequency band, adaptively selected relative frequency band, proposed a new feature extracting algorithm based on wavelet packet transform (WPTC), the experimental results show that the new feature has very good robustness under different kinds of noises, and different SNRs, and it plays a very good foreshadowing role in the latter speech research.