计算机工程2011，Vol.37Issue(2)：197-199,3.DOI:10.3969/j.issn.1000-3428.2011.02.068
基于DDBHMM的维吾尔语音声学识别
Uyghur Speech Acoustics Recognition Based on DDBHMM
摘要
Abstract
DDBHMM(Duration Distribution Based HMM) is adopted as the acoustic model for Uyghur continuous speech recognition, and the context-dependant triphone model is selected as the best recognition unit, the Uyghur speech recognition system is optirnised by using the state-binding method.In order to make the models be trained more sufficiently to improve the recognition performance, the corpus is enlarged, the emphasis is on analysis of the effect that the speech database's enlargement brings to the recognition rate and accuracy and so on based on several groups of contrasted experiments.关键词
语料库/维吾尔语/DDBHMM模型理论/三音子Key words
corpus/ Uyghur/ DDBHMM model theory/ triphone分类
自科综合引用本文复制引用
王飞飞,吾守尔·斯拉木,那斯尔江·吐尔逊..基于DDBHMM的维吾尔语音声学识别[J].计算机工程,2011,37(2):197-199,3.基金项目
国家自然科学基金资助项目(60762006,60863008) （60762006,60863008）
国家语委基金资助重点项目(MZ115-75) （MZ115-75）
