基于神经网络的语音识别研究  

Speech Recognition Based on Neural Networks

作　　者：叶虹[1] 祝永华[1] 张有正[1] 

机构地区：[1]浙江工业大学浙西分校,衢州324000

出　　处：《科学技术与工程》2010年第19期4797-4800,共4页Science Technology and Engineering

基　　金：浙江省自然科学基金项目(Y1090758)资助

摘　　要：提出了一种基于双权值神经网络的非特定人连续语音识别的新算法。这种算法可以不经过端点检测和分割,构建连续语音中各不同音节的特征空间覆盖区,可以避免因分割错误而带来的错误识别。通过实验得到了较为满意的识别结果。Two weight neural network is described. A new dynamic searching algorithm based on two weight neural network is presented. And then it was applied to recognize the continuous speech of speaker-independent. The recognition results can be searched dynamically without endpoint detecting and segmenting. Different feature- space covers are constructed according to different classes of syllables. Some satisfactory recognition results are ob- tained by experiment.

关 键 词：双权值神经网络 连续语音 语音识别 

分 类 号：TN912.34[电子电信—通信与信息系统]