首页 | 本学科首页   官方微博 | 高级检索  
     

基于加权全局时频特征的易混淆词识别
引用本文:顾明亮 王太君. 基于加权全局时频特征的易混淆词识别[J]. 应用科学学报, 1998, 16(3): 320-325
作者姓名:顾明亮 王太君
作者单位:东南大学
基金项目:国家攀登计划认知科学(神经网络)重大关键资助
摘    要:针对易混淆词特征差异小,分类决策困难的特点,提出了一种新的语音识别特征。该特征可以根据待识单词的发音特点,通过选用合适的基函数及加权处理,突出混淆词特征之间的差异性;

关 键 词:易混淆词识别 语音识别 全局时频特征 DHMM

WGTF Feature Based Confusing Word Recognition
GU MINGLIANG WANG [WT.BZ]TAIJUN SHI XIAOXING HE ZHENYA. WGTF Feature Based Confusing Word Recognition[J]. Journal of Applied Sciences, 1998, 16(3): 320-325
Authors:GU MINGLIANG WANG [WT.BZ]TAIJUN SHI XIAOXING HE ZHENYA
Affiliation:GU MINGLIANG WANG [WT10.5BZ]TAIJUN SHI XIAOXING HE ZHENYA
Abstract:This paper presents a novel feature (Weighted Global Time Frequency feature, i.e WGTF) for confusing word speech recognition, which enhances the difference among different confusing words by selecting proper base fuctions and weighting functions. Meanwhile, the storng discriminative power of artificial neural network has been used as a classifier to further raise the recognition rate. The experiment shows that the proposed method outperforms the standard DHMM and other ANN based method.
Keywords:vocal tract model   weighting function   GTF feature   speech recognition   neural network
本文献已被 CNKI 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号