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
收藏
页码：117 / 126
页数：10
相关论文
共 27 条
[21]   ADAPTIVE CEPSTRAL ANALYSIS OF SPEECH [J].
TOKUDA, K ;
KOBAYASHI, T ;
IMAI, S .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1995, 3 (06) :481-489
[22]  
WOLFEL M, 2003, P IEEE AUT SPEECH RE, P387
[23]  
WOLFEL M, 2004, ISCA P INT C SPOK LA
[24]  
WOLFEL M, 2003, ISCA P EUR, P1021
[25]   Development of a Sign Language Dialogue System for a Healing Dialogue Robot [J].
Huang, Xuan ;
Wu, Bo ;
Kameda, Hiroyuki .
2021 IEEE INTL CONF ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, INTL CONF ON PERVASIVE INTELLIGENCE AND COMPUTING, INTL CONF ON CLOUD AND BIG DATA COMPUTING, INTL CONF ON CYBER SCIENCE AND TECHNOLOGY CONGRESS DASC/PICOM/CBDCOM/CYBERSCITECH 2021, 2021, :867-872
[26]  
Yapanel U. H., 2003, ISCA P EUR, P1281
[27]  
YEGNANARAYANA B, 1977, P IEEE INT C AC SPEE, P20
123