|
|||||
|
|
| 基于三音素动态贝叶斯网络模型的大词汇量连续语音识别 | |
| 引用本文： | 吕国云,赵荣椿,张艳宁,樊养余,Sahli Hichem.基于三音素动态贝叶斯网络模型的大词汇量连续语音识别[J].数据采集与处理,2009,24(1). |
| 作者姓名： | 吕国云 赵荣椿 张艳宁 樊养余 Sahli Hichem |
| 作者单位： | 1. 西北工业大学电子信息学院,西安,710072 2. 西北工业大学计算机学院,西安,710072 3. 布鲁塞尔自由大学电子与信息处理系,比利时,布鲁塞尔,B-1050 |
| 基金项目： | 中国博士后科学基金，国家高技术研究发展计划(863计划) |
| 摘 要： | 考虑连续语音中的协同发音现象,基于词-音素结构的DBN(WP-DBN)模型和词-音素-状态结构的DBN(WPS-DBN)模型,引入上下文相关的三音素单元,提出两个新颖的单流DBN模型:基于词-三音素结构的DBN(WT-DBN)模型和基于词-三音素-状态的DBN(WTS-DBN)模型.WTS-DBN模型是三音素模型,识别基元为三音素,以显式的方式模拟了基于三音素状态捆绑的隐马尔可夫模型(HMM).大词汇量语音识别实验结果表明:在纯净语音环境下,WTS-DBN模型的识别率比HMM,WT-DBN,WP-DBN和WPS-DBN模型的识别率分别提高了20.53%,40.77%,42.72%和7.52%. |
| 关 键 词： | 语音识别 动态贝叶斯网络 三音素 音素 |
Continuous Speech Recognition for Large Vocabulary Based on Triphone DBN Model |
|
| Lü Guoyun,Zhao Rongchun,Zhang Yanning,Fan Yangyu,Sahli Hichem.Continuous Speech Recognition for Large Vocabulary Based on Triphone DBN Model[J].Journal of Data Acquisition & Processing,2009,24(1). | |
| Authors: | Lü Guoyun Zhao Rongchun Zhang Yanning Fan Yangyu Sahli Hichem |
| Abstract: | To avoid coarticulatory effects in continuous speech recognition,based on word-phone structure dynamic bayesian network(WP-DBN) model and word-phone-state structure DBN(WPS-DBN) model,context-dependent triphone units are introduced.Two novel single stream DBN models,that is,word-triphone structure DBN(WT-DBN) and word-triphone-state structure DBN(WTS-DBN) models,are proposed for continuous speech recognition.WTS-DBN model is a triphone model and its modeling unit is triphone.It simulates a conventional HMM(... |
| Keywords: | speech recognition dynamic Bayesian network triphone phone |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |