|
|||||
|
|
| 维吾尔语广播新闻连续语音敏感词检索系统 | |
| 引用本文： | 木合塔尔·沙地克,李晓,布合力齐姑丽·瓦斯力. 维吾尔语广播新闻连续语音敏感词检索系统[J]. 计算机系统应用, 2012, 21(3): 29-35,71 |
| 作者姓名： | 木合塔尔·沙地克 李晓 布合力齐姑丽·瓦斯力 |
| 作者单位： | 1. 中国科学院新疆理化技术研究所,乌鲁木齐830011;中国科学院研究生院,北京100084 2. 中国科学院新疆理化技术研究所,乌鲁木齐,830011 3. 新疆教育学院数学与信息技术分院,乌鲁木齐,830043 |
| 摘 要： | 首先介绍语音信号来源于新疆人民广播电台维吾尔语新闻的敏感词语音语料库的建设。然后用该语料库进行基于HMM的模型训练。模型训练中详细介绍识别基元端点检测、特征提取、矢量量化、码本构建、HMM模型训练过程和结果。最后用该语料库和HMM训练模型对维吾尔语广播新闻连续语音信号进行敏感词检索,并对检索结果进行分析。 |
| 关 键 词： | 语音语料库 敏感词检索 维吾尔语 单词分割 连续语音识别 |
| 收稿时间： | 2011-07-08 |
| 修稿时间： | 2011-08-07 |
Uyghur Broadcast News Continues Speech Sensitive-Word Spotting System |
|
| MU He Ta Rr Sha di ke,LI Xiao and BU He Li Qi Gu Li Wa Si Li. Uyghur Broadcast News Continues Speech Sensitive-Word Spotting System[J]. Computer Systems& Applications, 2012, 21(3): 29-35,71 | |
| Authors: | MU He Ta Rr Sha di ke LI Xiao BU He Li Qi Gu Li Wa Si Li |
| Affiliation: | MU He Ta Rr Sha di ke, LI Xiao, BU He Li Qi Gu Li Wa Si Li(1.Xinjiang Technical Institute of Physics ＆ Chemistry, Chinese Academy of Sciences, Urumchi 830011, China;2.Graduate School, Chinese Academy of Sciences, Beijing 100084, China; 3.College of Mathematic and Information Technology, Xinjiang Education Institute, Urumchi 830043, China) |
| Abstract: | First, this paper introduces the design a corpus based on Uighur news of Xinjiang Broadcast Station. And then, Training the HMM for this corpus. In this step, introduces Word Segmentation, Feature Extraction, Vector Quantization, Codebook, HMM Training etc. Finally, use the corpus and training model implements HMM based Uyghur broadcast news continues speech Sensitive-word spotting and give the conclusion of the test. |
| Keywords: | corpus sensitive-word Spotting Uyghur word Segmentation continues speech recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《计算机系统应用》浏览原始摘要信息 | |
| 点击此处可从《计算机系统应用》下载全文 | |