Minimum variance distortionless response spectral estimation

被引：64

作者：

Wölfel, M

McDonough, J

机构：

[1] Interactive Systems Laboratories, Universität Karlsruhe (TH), Karlsruhe

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 2005年 / 22卷 / 05期

关键词：

D O I：

10.1109/MSP.2005.1511829

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Spectral estimation techniques are useful in extracting features to be used by an automatic speech recognition (ASR) system. Such techniques are widely used in the feature extraction process of an automatic speech recognition (ASR) system, including the power spectrum, linear prediction (LP), and warped-linear prediction (WLP) methods.The minimum variance distortionless response (MVDR) envelope is proved to be superior to LP for modeling the spectra of voiced speech.

引用

页码：117 / 126

页数：10

共 27 条

[1]

BARKER J, 1997, ISCA P EUR, P2127

[2] RELATIONSHIP BETWEEN MAXIMUM ENTROPY SPECTRA AND MAXIMUM LIKELIHOOD SPECTRA [J].