| 汉语连续语音识别的语速自适应算法 |
| |
| 引用本文： | 王作英, 李健. 汉语连续语音识别的语速自适应算法[J]. 声学学报, 2003, 28(3): 229-234. DOI: 10.15949/j.cnki.0371-0025.2003.03.007 |
| |
| 作者姓名： | 王作英 李健 |
| |
| 作者单位： | 清华大学电子工程系,北京,100084;清华大学电子工程系,北京,100084 |
| |
| 摘 要： | 在连续语音中,不同的说话者在不同语境下说话的速度差异是很大的。偏离正常语速往往会造成识别错误,使识别性能下降。考虑到语速对于语音单元段长的影响是同步增长或同步下降的,相邻语音单元的段长之间存在很强的相关性,本文从利用段长的相关信息出发,在基于段长分布的隐含马尔可夫模型(DDBHMM:Duration Distribution Based HMM)的框架上,提出了一种语速自适应算法。对数字串和大词汇量连续语音识别的试验表明这个算法是有效的。
|
| 收稿时间： | 2002-03-05 |
| 修稿时间： | 2002-05-10 |
The speaking rate adaptation algorithm in Putonghua continuous speech recognition |
| |
| WANG Zuoying, LI Jian. The speaking rate adaptation algorithm in Putonghua continuous speech recognition[J]. ACTA ACUSTICA, 2003, 28(3): 229-234. DOI: 10.15949/j.cnki.0371-0025.2003.03.007 |
| |
| Authors: | WANG Zuoying LI Jian |
| |
| Affiliation: | 1.Department of Electronic Engineering, Tsinghua University Beijing 100084 |
| |
| Abstract: | In continuous speech, the difference of speaking rates is big among speakers in different speaking environment. The variation of the speaking rates can cause recognition errors and affect the performance of LVCSR(Large Vocabulary Continuous Speech Recognition) systems. It is noted that the duration of neighboring speech units, which is affected by speaking rates, increases or decreases synchronously and a strong correlation exits between them. Based on the framework of DDBHMM (Duration Distribution Based HMM), a speaking rate adaptation algorithm is proposed. For utilizing the correlation information between duration of neighboring speech units. The experiments on connected digit and large vocabulary continuous speech show that the new algorithm is effective. |
| |
| Keywords: | |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《声学学报》浏览原始摘要信息 |
|
点击此处可从《声学学报》下载全文 |
|
