Joint wavelet transform and vector quantization for speech coding

A new scheme for speech compression is presented using both discrete wavelet transform (DWT) and vector quantization (VQ). This method named discrete wavelet vector transform quantization (DWVTQ) is a coding system in which the speech signal is transformed into wavelet coefficients corresponding to different frequency bands which are vector quantized separately. The proposed implementation uses product code structure for each frequency band. The bit assignment of vector codes is adapted taking into account both the statistics of the wavelet coefficients and the fact that the human ear is less sensitive in the high-frequency bands. Vector quantization design procedures for discrete wavelet transformed speech and simulation results are presented. These results show the efficiency of DWVTQ over discrete wavelet scalar transform quantization (DWSTQ) of the transformed speech, and improvement of the optimal bit allocation in comparison to uniform bit allocation