基于SFCM自适应矢量量化码本训练方法

Code Training Method of Self-Adaptation Vector Quantization Based on SFCM Algorithm

自适应矢量量化在语音信号处理中有广泛地应用 ,提出了一种基于SFCM算法的自适应矢量量化码本的训练方法 ,其特点是通过模糊聚类方法 ,重新调整训练样本与码字之间的隶属度 ,达到最小编码失真 ,使码本更适合新说话人 ,且计算简单·实验结果表明 ,可以使编码平均失真下降·

In speech signal processing, the self adaptation vector quantization is widely used. The code training method of self adaptation vector quantization based on SFCM algorithm was proposed. The membership between training samples and codebook is readjusted and the least coding distortion is reached by the fuzzy clustering method. The codebook is more adapt to new speaker. The calculation of this method is simple. The coding average distortion is low.