文章基本信息

标题：Analysis of MFCC & Multitaper MFCC Feature Extraction for Speaker Verification
本地全文：下载
作者：Rupali G Shintri ; Asst.Prof S.K.Bhatia
期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：5
页码：4833-4836
出版社：TechScience Publications
摘要：In speech & audio applications, short-term signal spectrum is often represented using mel-freuency cepstral coefficient (MFCC) computed from a windowed discrete Fourier transform (DFT). Windowing reduces spectral leakage but variance of the spectrum estimate remains high. An extension to windowed DFT is called multitaper method which uses multiple time domain windows which are called as tapers with frequency domain averaging. Then detailed statistical analysis of MFCC bias & variance is done. For speaker verification the extracted feature is used to build a model using classifier (GMM), which implements likelihood ratio test to decide whether to accept or reject the speaker.
关键词：Mel-frequency cepstral coefficient; multitaper;GMM; speaker verification; tapers