基于梅尔频率倒谱系数与翻转梅尔频率倒谱系数的说话人识别方法

Speaker recognition method based on Mel frequency cepstrum coefficient and inverted Mel frequency cepstrum coefficient

为提高说话人识别系统的识别率,提出了基于梅尔频率倒谱系数(MFCC)与翻转梅尔频率倒谱系数(IMFCC)为特征参数的特征提取新方法。该方法利用Fisher准则将MFCC和IMFCC相结合,构造了一种混合特征参数。实验结果表明,新的混合特征参数与MFCC相比,在纯净语音库及噪声环境中均具有较好的识别性能。

To improve the performance of speaker recognition system, a new method of feature extraction was proposed based on Mel Frequency Cepstrum Coefficient （MFCC） and Inverted MFCC （IMFCC）. This method constructed a mixed feature by combining MFCC with IMFCC using Fisher criterion. The experimental results show that the mixed feature proposed in this paper has better recognition performance compared with MFCC not only in the pure voice database but also in the noisy environments.