CAJ | 학술논문

Mel倒谱系数(MFCC)侧重提取语音信号的低频信息，对语音信号的频谱分布特性描述不充分，不能有效区分说话人个性信息。为此，通过分析语音信号各频段所含说话人个性信息的不同，结合Mel滤波器和反Mel滤波器在高低频段的不同特性，提出一种适于说话人识别的改进 Mel 滤波器。实验结果表明，改进 Mel 滤波器提取的新特征能够获得比传统 Mel 倒谱系数以及反Mel倒谱系数(IMFCC)更好的识别效果，并且基本不增加说话人识别系统训练和识别的时间开销。
Mel도보계수(MFCC)측중제취어음신호적저빈신식，대어음신호적빈보분포특성묘술불충분，불능유효구분설화인개성신식。위차，통과분석어음신호각빈단소함설화인개성신식적불동，결합Mel려파기화반Mel려파기재고저빈단적불동특성，제출일충괄우설화인식별적개진 Mel 려파기。실험결과표명，개진 Mel 려파기제취적신특정능구획득비전통 Mel 도보계수이급반Mel도보계수(IMFCC)경호적식별효과，병차기본불증가설화인식별계통훈련화식별적시간개소。
Mel-frequency Cepstral Coefficient(MFCC) focuses on extracting information in the lower frequency of speech signal, and fails to describe the distribution of a speech spectrum sufficiently, so it cannot effectively distinguish speaker’s specific information. By analyzing the distribution of speaker specific information in different frequency bands of the speech signal, different characters of mel-filterbank and inverted mel-filterbank are combined in high and low frequency bands, and an improved filterbank is presented, which is more suitable for speaker recognition. Experimental results show that features are extracted using the improved filterbank achieve better recognition rates compared with the traditional MFCC and Inverted MFCC, and without increasing the computing time obviously.