关键词: 识别精度, 梅尔倒谱系数, 逆梅尔倒谱系数, 中频梅尔倒谱系数, Fisher准则

Abstract: Concerning the low identification precision of Mel Frequency Cepstral Coefficients (MFCC) parameters in high frequency signals and the problem that the influence of each dimension feature parameters has not been considered to identify, the method of extracting features based on MFCC, IMFCC (Inverted MFCC) and MidMFCC (Mid-frequency MFCC) combined with Fisher criterion was adopted. Extracting MFCC, IMFCC and MidMFCC parameters from speech signals and calculating the Fisher ratio of components of three parameters, useful parameters were chosen by using Fisher standard and a mixture feature was constructed to improve mid-frequency and high frequency recognition accuracy. The experimental results show that the new feature has better recognition results compared with MFCC in the same environment.

Key words: recognition accuracy, Mel Frequency Cepstral Coefficients(MFCC), Inverted MFCC, Mid-frequency MFCC, Fisher criterion