[1]成德源,张小绵.电话频带汉语普通话连续语音识别[J].深圳大学学报理工版,1996,(1-2):24-26.
 Cheng Deyuan and Zhang Xiaomian.Telephone Band Continuous Speech Recognition for Chinese Mandarin[J].Journal of Shenzhen University Science and Engineering,1996,(1-2):24-26.
点击复制

电话频带汉语普通话连续语音识别()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
期数:
1996年1-2期
页码:
24-26
栏目:
电子与信息科学
出版日期:
1996-06-30

文章信息/Info

Title:
Telephone Band Continuous Speech Recognition for Chinese Mandarin
作者:
成德源张小绵
深圳大学电子工程系,深圳518060
Author(s):
Cheng Deyuan and Zhang Xiaomian
Dept. of Electronic Engineering, Shenzhen University Shenzhen 518060. P.R China
分类号:
TN912.34
摘要:
基于帧能量参数和帧与稳态背景噪声状态之间的失真度,将连续的电 话频带汉语语音信号分割至用隐马尔可夫链模型表示的以字为单位的语音,采用动 态时间规正算法和最小失真度准则,作以字为单位的语音识别,从而实现连续语音识 别.实验表明电话频带连续语音识别正确率达到75%.
Abstract:
Based on the frame energy parameter and the distortion between a frame signal and stable background noise state, an utterance of telephone band Chinese continuous speech signal is divided into character speech that is characterized using Hidden Markov Model (HMM). Using dynamic time warping algorithm and minimizing the distortion, the isolated character speech recognition is performed. Thus continuous speech recognition is realized. The experiments showed that correct rate for the telephone band continuous speech recognition was 75%.
更新日期/Last Update: 2016-04-26