Research on the Application of Biomimetic Computing in Speech Recognition
Since speech is one of the most direct and effective means of human communication, its natural to apply biomimetic processing mechanism to automatic speech recognition to solve the existing speech recognition problems. In this paper, three typical techniques were selected respectively: simulated evolutionary computation(SEC), artificial neural network(ANN) and fuzzy logic and reasoning technique, from intelligence building processing simulation, intelligence structure simulation and intelligence behavior simulation, to identify their applications in different stages of speech recognition. A SEC usage and the corresponding algorithm were presented to generate training speech data, and a method of Elman network as acoustic model was also presented.
Chunyi Guo Runzhi Li Lei Shi
School of Information Engineering, Zhengzhou University Zhengzhou, Henan, China Henan Provincial Key Lab on Information Network, Zhengzhou University
国际会议
2008 International Conference on Audio，Language and Image Processing(2008国际声音、语言、图像过程大会)
镇江
英文
45-49
2008-07-07（万方平台首次上网日期，不代表论文的发表时间）