基于时频特征的说话人识别研究-模式识别与智能系统专业论文.docxVIP

Abstract Abstract Speaker recognition is an authentication of biological to identi句 speaker according to the voice，widely used in speech retrieval，judicial identification，computer remo阳 login，safety certificate ，etc. Because of its wide application，由e speaker recognition has become a hot spot of research in the field of biological anthentication technology today. The speaker recognition attention is paid to the speech signal in the speakers personality factors，emphasized the difference between different people，which requires the speaker feature extraction 阳 very precise. Although there have been various extraction method，there 町e some difficulties by duing to the environment and speak in ones own various factors. This paper focus on the speakers time-frequency feature，and the main research works areωfollow: 1.This paper puts forward a time-frequency method based on Gabor transform and bilinear time唰仕equency distribution of combining. According to 由e shorttime Fourier transform ，Wigner-Ville distribution，Choi-Williams such as distribution of time-frequency analysis problems，from the Angle of image processing of Gabor transform and bilinear time-frequency distribution oftime-仕equency combination after image processing technology ， can get good time-frequency gathered sex also reduced cross terms of time-frequency distribution. Simmulation results which are compared wi由 Gabor transform ，Wi伊gn盯er-Vi让lle distribution and Cαh创oi-Wi川llia缸rm四s distribution 让it can g创ain finer time. .η町ough the front speech time仕equency structure，using MelFrequency Cepstrum Coefficients as the characteristic parameters for speaker recognition. First，respectively extractint the Mel frequency cepstrum parameters of primitive voice，various respectively on time仕equency analysis methods and the improved time壮equency structure，and then use support vector machine for speaker rec。但ition.Simulation experiments show that 伽e improved time仕equency structure is more useful to improve speaker