Font Size: a A A

Research Of Speech Recognition In Embedded System

Posted on:2007-03-03Degree:MasterType:Thesis
Country:ChinaCandidate:L WeiFull Text:PDF
GTID:2178360182482260Subject:Mechanical and electrical engineering
Abstract/Summary:PDF Full Text Request
The speech recognition technology is the important developing direction of the computer technology, with the development of people's standard of living, it is more and more people to use the computer .It has already become the key technology that the computer communicate with people well, and will become significant technology of the information industry and important characteristic of the computer in the future.At present, the speech recognition technology has been already used widely, but the embedded speech recognition products are few among people's daily life, this field has wide market prospects.Under this background, on the basis of studying the speech recognition technology deeply, offer a scheme that is suited to speaker-independent and small-scale vocabulary speech recognition system based on SPCE061 A controller. It can combined with machine translation and speech synthesis to realize the embedded system that can translate english to Chinese, applying it to people's daily life, improving the quality of people's daily life.This paper includes the following aspects:(1) Firstly, it introduces the research and development of speech recognition , also includes the existing problems, summarize the theory of speech recognition, laiding a good foundation for further study of speech recognition.(2) After has done a very good summary in preprocessing technology of the speech recognition, it particular analyses the preprocessing technology, integrating the advantage of them, giving necessary instruction to realize the system, and also about model-training and model-match.(3) According analyse the way of feature parameter extraction, we get the principle of feature parameter extraction, also study the theory of the model-training and model- matching.(4) Design a system that is suited to speaker-independent and small-scale vocabulary speech recognition based on the SPCE061A controller, preliminary realization tothe system in some small-scale vocabulary is carried on.A conclusion of paper is made in the end, we also points out the flaw of the system, then presents the orientation of subsequent research work.
Keywords/Search Tags:feature parameter extraction, embedded, preprocessing model-training, speech recognition
PDF Full Text Request
Related items