| 基于DDBHMM的维吾尔语音声学识别 |
| |
| 引用本文： | 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. |
| |
| 作者姓名： | 王飞飞 吾守尔·斯拉木 那斯尔江·吐尔逊 |
| |
| 作者单位： | 1. 新疆大学信息科学与工程学院,乌鲁木齐,830046
2. 新疆大学数学与系统科学学院,乌鲁木齐,830046;西安交通大学电子与信息工程学院,西安710049 |
| |
| 基金项目： | 国家自然科学基金资助项目(60762006,60863008); 国家语委基金资助重点项目(MZ115-75) |
| |
| 摘 要： | 在维吾尔语连续语音识别试验的声学层建模基础上，引用DDBHMM模型将上下文相关的三音子作为基本识别单元，并提出一种状态绑定的思想，对状态进行优化。为得到更充分的训练模型，提高识别效率，对语料库进行扩充，在多组对比试验的基础上，分析扩充前后对声学层识别速度、准确率等各个方面的影响。
|
| 关 键 词： | 语料库 维吾尔语 DDBHMM模型理论 三音子 |
Uyghur Speech Acoustics Recognition Based on DDBHMM |
| |
| WANG Fei-fei,Wushour Silamu,Nasirjan Tursun.Uyghur Speech Acoustics Recognition Based on DDBHMM[J].Computer Engineering,2011,37(2):197-199. |
| |
| Authors: | WANG Fei-fei Wushour Silamu Nasirjan Tursun |
| |
| Affiliation: | WANG Fei-fei1a,Wushour Silamu1a,Nasirjan Tursun1b,2(1a.Information Science and Engineering College,1b.Mathematics and Systems Science College,Xinjiang University,Urumqi 830046,China,2.Electronic and Information Engineering College,Xi'an Jiaotong University,Xi'an 710049,China) |
| |
| Abstract: | DDBHMM(Duration Distribution Based HMM) is adopted as the acoustic model for Uyghur continuous speech recognition,and the context-dependent triphone model is selected as the best recognition unit,the Uyghur speech recognition system is optimised 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 a... |
| |
| Keywords: | corpus Uyghur DDBHMM model theory triphone |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
|
