文件名称:Gammashirp-filter
介绍说明－－下载内容均来自于网络，请自行研究使用
In this paper, we figure out the use of appended jitter and shimmer speech features for closed set text
independent speaker identification system. Jitter and shimmer features are extracted from the
fundamental frequency contour and added to baseline spectral features, specifically Mel-frequency
Cepstral Coefficients (MFCCs) for human speech and MFCC-GC which integrate the Gammachirp
filterbank instead of the Mel scale. Hidden Markov Models (HMMs) with Gaussian Mixture Models
(GMMs) state distributions are used for classification. Our approach achieves substantial performance
improvement in a speaker identification task compared with a state-of-the-art robust front-end in a
clean condition.
independent speaker identification system. Jitter and shimmer features are extracted from the
fundamental frequency contour and added to baseline spectral features, specifically Mel-frequency
Cepstral Coefficients (MFCCs) for human speech and MFCC-GC which integrate the Gammachirp
filterbank instead of the Mel scale. Hidden Markov Models (HMMs) with Gaussian Mixture Models
(GMMs) state distributions are used for classification. Our approach achieves substantial performance
improvement in a speaker identification task compared with a state-of-the-art robust front-end in a
clean condition.
(系统自动生成,下载前可以参看下载内容)
下载文件列表
Gammashirp filter.pdf