TEMPORAL CONTROL IMPROVEMENT OF HIDDEN MARKOV-MODELS FOR AUTOMATIC SPEECH RECOGNITION

被引:0
|
作者
DOURSSENAC, C [1 ]
机构
[1] UNIV TOULOUSE 3,IRIT LAB,CNRS,URA 1399,F-31062 TOULOUSE,FRANCE
来源
MICROPROCESSING AND MICROPROGRAMMING | 1991年 / 32卷 / 1-5期
关键词
19;
D O I
10.1016/0165-6074(91)90400-N
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
A contribution for speaker-independent recognition systems is presented, as well for speech recognition in the presence of large vocabularies as for word spotting. The recognition strategy used is based upon continuous hidden markov models (HMMs) which include two levels (phonemic level and word level). The aim of the method is double; first to provide a fast algorithm for sub-vocabulary preselection or recognition in the presence of small vocabulary, second to improve the temporal control of the standard HMMs.
引用
收藏
页码:549 / 556
页数:8
相关论文
共 50 条