The server is under maintenance between 08:00 to 12:00 (GMT+08:00), and please visit later.
We apologize for any inconvenience caused
Login  | Sign Up  |  Oriprobe Inc. Feed
China/Asia On Demand
Journal Articles
Laws/Policies/Regulations
Companies/Products
A Model for Recognition of Isolated Words in Noisy Environments
Author(s): 
Pages: 659-665
Year: Issue:  6
Journal: JOURNAL OF CHINA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Keyword:  连续隐Markov模型人工神经网络噪声鲁棒性语音识别;
Abstract: 论文提出了一种连续隐Markov模型和BP神经网络相结合的、具有两次辨识过程的抗噪孤立字识别模型.首先以连续隐Markov模型完成语音信号的时序建模并提供一次识别信息;以BP神经网络进行后处理,提取二次识别信息,识别结果由两次识别信息共同决定.实验证明,由于有效地利用了隐Markov模型的强时序信号处理能力和BP神经网络的强模式分类和泛化性能,这种识别模型明显地改善了孤立字识别系统的抗噪性能.
Related Articles
loading...