A LD-aCELP Speech Coding Algorithm Based on Modified SOFM Vector Quantizer

According to the character of codebook size and codeword dimension in low delay speech coding algorithm, a codebook design algorithm based on modified self-organizing feature map (SOFM) neural network is put forward. The input vectors and weight vectors are normalized. In order to reduce the computation complexity and improve the codebook performance, decompose the adaptive adjusting process of network weights into two stages of sequencing and convergence. The modified algorithm is used to generate vector quantization codebook in low delay speech coding algorithm experiment results show that the modified algorithm improves the performance of SOFM network significantly. Compared with the basic LBG algorithm, the synthesized speech using codebook with the modified SOFM neural network are greatly improved in the aspect of subjective and objective quality.