首页 | 本学科首页   官方微博 | 高级检索  
     

语音识别中基于模糊聚类分析的参数聚类
引用本文:徐向华,朱杰,郭强. 语音识别中基于模糊聚类分析的参数聚类[J]. 上海交通大学学报, 2004, 38(12): 2086-2088,2093
作者姓名:徐向华  朱杰  郭强
作者单位:上海交通大学,电子工程系,上海,200030
基金项目:上海市科委重点基金资助项目(01JC14033)
摘    要:为减少语音识别中声学模型的参数量,提高参数训练的鲁棒性,基于声学决策树结构,提出利用模糊聚类分析方法对模型参数聚类,包括高斯聚类和方差共享.对大词汇量汉语连续语音识别的实验结果表明:高斯模糊聚类使高斯数减少25%时,识别率提高了0.15%.进一步做模糊方差共享,当方差减少到初始模型的24%,与同样参数量的未进行聚类的模型相比,误识率下降了3.01%,证明了模糊聚类分析在语音参数聚类中的有效性.

关 键 词:语音识别 模糊聚类分析 决策树状态聚类
文章编号:1006-2467(2004)12-2086-03

Parameter Clustering Based on Fuzzy Clustering Analysis in Speech Recognition
XU Xiang-hua,ZHU Jie,GUOQiang. Parameter Clustering Based on Fuzzy Clustering Analysis in Speech Recognition[J]. Journal of Shanghai Jiaotong University, 2004, 38(12): 2086-2088,2093
Authors:XU Xiang-hua  ZHU Jie  GUOQiang
Abstract:In order to decrease the parameter size of acoustic models in speech recognition and improve the robustness of parameter training, a fuzzy clustering analysis method was used for parameter clustering. Based on the structure of phonetic decision tree, the proposed parameter clustering method includes Gaussians clustering and covariance sharing. The experimental results on large vocabulary continuous Mandarin speech recognition show when the number of Gaussians is reduced by 25%, the recognition accuracy increases by 0.15%. Combined with covariance sharing, 24% covarinaces achieve 3.01% error rate reduction over the system with approximately the same parameter size. These results prove the effectiveness of fuzzy clustering in speech recognition.
Keywords:speech recognition  fuzzy clustering analysis  decision tree based state tying
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号