BP NURAL NETWORK OPTIMIZATION IN SPEECH RECOGNITION

摘要：

The speech signal is a complicated function influenced by factors such as the speaker, environment, etc.The artificial neural network (ANN) model carries on speech recognition with characteristics such as self-adaptation selforganization and self-imagination, suitable for speech recognition.This paper mainly studies the improvement scheme of traditional BP neural network in speech recognition.By making use of the scheme after improving, it can simplify network structure, accelerate operation, and shorten the training time.

关键词： ANN Back propagation algorithm speech recognition warping network

作者: CUI BING-DE

作者单位: Computer Science Department Hebei Engineering and Technical College Cangzhou,HeBei,China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Computer Technology and Development(2011第三届计算机技术与发展国际会议 ICCTD2011)

会议地点: 成都

会议语种:英文

页码: 33-36

在线出版日期: 2011-11-25（万方平台首次上网日期，不代表论文的发表时间）