|
|||||
|
|
| Subspace Distribution Clustering HMM for Chinese Digit Speech Recognition | |
| 引用本文： | QIN Wei WEI Gang. Subspace Distribution Clustering HMM for Chinese Digit Speech Recognition[J]. 中国电子科技, 2006, 4(1): 43-46 |
| 作者姓名： | QIN Wei WEI Gang |
| 作者单位： | College of Electronics and Communications, South China University of Technology Guangzhou 510640 China |
| 基金项目： | Supported by the National Natural Science Foundation of China （No.60172048） |
| 摘 要： | As a kind of statistical method, the technique of Hidden Markov Model （HMM） is widely used for speech recognition. In order to train the HMM to be more effective with much less amount of data, the Subspace Distribution Clustering Hidden Markov Model （SDCHMM）, derived from the Continuous Density Hidden Markov Model （CDHMM）, is introduced. With parameter tying, a new method to train SDCHMMs is described. Compared with the conventional training method, an SDCHMM recognizer trained by means of the new method achieves higher accuracy and speed. Experiment results show that the SDCHMM recognizer outperforms the CDHMM recognizer on speech recognition of Chinese digits. |
| 关 键 词： | 语音识别 SDCHMM 子空间分布 Markov模型 CDHMM |
| 收稿时间： | 2005-09-21 |
Subspace Distribution Clustering HMM for Chinese Digit Speech Recognition |
|
| QIN Wei,WEI Gang. Subspace Distribution Clustering HMM for Chinese Digit Speech Recognition[J]. Journal of Electronic Science Technology of China, 2006, 4(1): 43-46 | |
| Authors: | QIN Wei WEI Gang |
| Abstract: | As a kind of statistical method, the technique of Hidden Markov Model (HMM) is widely used for speech recognition. In order to train the HMM to be more effective with much less amount of data, the Subspace Distribution Clustering Hidden Markov Model (SDCHMM), derived from the Continuous Density Hidden Markov Model (CDHMM), is introduced. With parameter tying, a new method to train SDCHMMs is described. Compared with the conventional training method, an SDCHMM recognizer trained by means of the new method achieves higher accuracy and speed. Experiment results show that the SDCHMM recognizer outperforms the CDHMM recognizer on speech recognition of Chinese digits. |
| Keywords: | speech recognition Subspace Distribution Clustering Hidden Markov Model (SDCHMM) Continuous Density Hidden Markov Model (CDHMM) parameter tying |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |