Decision tree based state tying for speech recognition using DNN derived embeddings | |
Li, Xiangang ; Wu, Xihong | |
2014 | |
关键词 | decision tree based state tying DNN embedding speech recognition clustering NEURAL-NETWORKS |
英文摘要 | Recently, context dependent (CD)-deep neural network (DNN)-hidden Markov model (HMM) obtains significant improvements in many automatic speech recognition (ASR) tasks. In the standard training procedure for CD-DNN-HMM, the Gaussian mixture models (GMM) based ASR system has to be firstly built to pre-segment the training data and to define the CD states as the targets for DNN. In this paper, we propose a novel decision tree based state tying procedure, in which, the state embeddings derived from DNN are used and clustered to minimize the sum-of-squared error. Thus, the GMM is not a necessary part to define the targets for CD-DNN. Besides, we introduce a training procedure for CD-DNN-HMM, where, the forward backward algorithm is used for context independent (CI) DNN-HMM training, and the proposed state tying approach is applied to define the CD-DNN targets. Experiments were conducted on a 30-hour Chinese broadcast news speech database and the results demonstrate that the proposed DNN based state tying approach yielded comparable performance to the GMM based one.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000349765600026&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Computer Science, Artificial Intelligence; CPCI-S(ISTP); 0 |
语种 | 英语 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/292409] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Li, Xiangang,Wu, Xihong. Decision tree based state tying for speech recognition using DNN derived embeddings. 2014-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论