An HMM/MFNN hybrid architecture based on stacked generalization for speaker identification | |
Bao, WQ ; Chen, K ; Chi, HS | |
1998 | |
关键词 | speaker identification stacked generalization HMM/MFNN hybrid architecture |
英文摘要 | A hybrid architecture based upon Hidden Markov Models (HMMs) and Multilayer Feed-forward Neural Network (MFNN) is presented for speaker identification. Unlike most of the previous combing methods, the proposed architecture uses HMMs to model individual speaker and uses MFNN to deal with the inter-speaker information for improving performance. Learning in the proposed architecture consists of two phases. In particular, only a small amount of data is needed for training. The HMM/MFNN architecture has been applied to text-independent speaker identification. Simulation has shown that the hybrid architecture yields better identifying rate than that of conventional methods and other hybrid architectures.; Computer Science, Artificial Intelligence; Computer Science, Interdisciplinary Applications; Engineering, Biomedical; Engineering, Electrical & Electronic; Medical Informatics; Neurosciences; CPCI-S(ISTP); 0 |
语种 | 英语 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/294025] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Bao, WQ,Chen, K,Chi, HS. An HMM/MFNN hybrid architecture based on stacked generalization for speaker identification. 1998-01-01. |
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