| Fuzzy C-Means Clustering Based Phonetic Tied-Mixture HMM in Speech Recognition |
| |
| 作者姓名： | 徐向华 朱杰 郭强 |
| |
| 作者单位： | Dept.ofElectronicEng.,ShanghaiJiaotongUniv.,Shanghai200030,China |
| |
| 基金项目： | Supported by the Science and TechnologyCommittee of Shanghai (0 1JC14 0 3 3 ) |
| |
| 摘 要： | A fuzzy clustering analysis based phonetic tied-mixture HMM (FPTM) was presented to decrease parameter size and improve robustness of parameter training. FPTM was synthesized from state-tied HMMs by a modified fuzzy C-means clustering algorithm. Each Gaussian codebook of FPTM was built from Gaussian components within the same root node in phonetic decision tree. The experimental results on large vocabulary Mandarin speech recognition show that compared with conventional phonetic tied-mixture HMM and state-tied HMM with approximately the same number of Gaussian mixtures, FPTM achieves word error rate reductions by 4.84% and 13.02% respectively. Combining the two schemes of mixing weights pruning and Gaussian centers fuzzy merging, a significantly parameter size reduction was achieved with little impact on recognition accuracy.
|
| 关 键 词： | 隐马尔可夫模型 语音识别 FCM 语言判定树 |
Fuzzy C-Means Clustering Based Phonetic Tied-Mixture HMM in Speech Recognition |
| |
| XU Xiang-hua,ZHU Jie,GUO Qiang.Fuzzy C-Means Clustering Based Phonetic Tied-Mixture HMM in Speech Recognition[J].Journal of Shanghai Jiaotong university,2005,10(1):16-20. |
| |
| Authors: | XU Xiang-hua ZHU Jie GUO Qiang |
| |
| Institution: | Dept.of Electronic Eng.,Shanghai Jiaotong Univ.,Shanghai 200030,China |
| |
| Abstract: | A fuzzy clustering analysis based phonetic tied-mixture HMM(FPTM) was presented to decrease parameter size and improve robustness of parameter training. FPTM was synthesized from state-tied HMMs by a modified fuzzy C-means clustering algorithm. Each Gaussian codebook of FPTM was built from Gaussian components within the same root node in phonetic decision tree. The experimental results on large vocabulary Mandarin speech recognition show that compared with conventional phonetic tied-mixture HMM and state-tied HMM with approximately the same number of Gaussian mixtures, FPTM achieves word error rate reductions by 4.84% and 13.02% respectively. Combining the two schemes of mixing weights pruning and Gaussian centers fuzzy merging, a significantly parameter size reduction was achieved with little impact on recognition accuracy. |
| |
| Keywords: | speech recognition hidden Markov model (HMM) fuzzy C-means (FCM) phonetic decision tree |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
