| 基于多空间概率分布的汉语连续语音声调识别研究 |
| |
| 引用本文： | 倪崇嘉,刘文举,徐波.基于多空间概率分布的汉语连续语音声调识别研究[J].计算机科学,2011,38(9):224-226. |
| |
| 作者姓名： | 倪崇嘉 刘文举 徐波 |
| |
| 作者单位： | (山东财政学院统计与数理学院 济南 250014);
(中国科学院自动化研究所模式识别国家重点实验室 北京 100190) |
| |
| 基金项目： | 本文受国家自然科学基金(90820303,60675026,90820011),国家高技术研究863计划(200601O1G4073,2006AAO1G194)和国家重点基础研究发展973计划(2004CB318105)资助。 |
| |
| 摘 要： | 汉语是一种带声调的语言,声调信息在汉语语音识别中具有非常重要的意义。提出了emt}eaaea声调模型与explicit声调模型相结合的方法用以识别汉语连续语音的声调。该方法能够将逐帧的基频信息和较强时长的基频信息相结合来识别声调。在“863-Test”和“TestCorpus98"测试集上的实验表明,该方法分别能够达到96. 12%和93.78 %的声调识别正确率。
|
| 关 键 词： | 声调 基频 多空间概率分布 |
Research about Tone Recognition of Mandarin Continuous Speech Based on Multi-space Probability Distribution |
| |
| NI Chong-ji,LIU Wen ju,XU Bo.Research about Tone Recognition of Mandarin Continuous Speech Based on Multi-space Probability Distribution[J].Computer Science,2011,38(9):224-226. |
| |
| Authors: | NI Chong-ji LIU Wen ju XU Bo |
| |
| Affiliation: | NI Chong-jia1,2 LIU Wen-ju2 XU Bo2(School of Statistics and Mathematics,Shandong University of Finance,Jinan 250014,China)1(National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China)2 |
| |
| Abstract: | Chinese Mandarin is the tonal language. Tone is important to Mandarin speech recognition. We proposed a method to recognize the tone of Mandarin continuous speech, which is the combination of embedded tone model and explicit tone model. This method can fuse the fundamental frequency information of short time and long time. The experimenu in "863-Test" and "TestCorpus98" test show that our proposed method can achieve 96. 12%and 93. 78% tone recognition correct rate separatively. |
| |
| Keywords: | Tone Fundamental freduency Multi-space probability distribution |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《计算机科学》浏览原始摘要信息 |
|
点击此处可从《计算机科学》下载全文 |
