Dissertation > Excellent graduate degree dissertation topics show

Research and Simulation on Speech Recognition in Noisy Environment

Author: LiuJianHui
Tutor: LuZuoXian
School: Wuhan University of Technology
Course: Communication and Information System
Keywords: Speech recognition endpoint detection linear prediction DTW
CLC: TN912.34
Type: Master's thesis
Year: 2006
Downloads: 470
Quote: 6
Read: Download Dissertation

Abstract


Since human being can make various machines and use them, the people have had an ideal that various machines could understand their language, and act according to their orally orders, thereby realizing the linguistic communion between the human and the machine. With the development of the technology, and the appearance of Speech Recognition Technology, the ideal of human being has realized. The Speech Recognition Technology is a high technology, which make the machine change the speech signals into homologous text or order by recognition and comprehend. The speech recognition technology is the important developing direction of the computer technology, it has already become the key technology that the computer has popularized among hundreds of millions of common people, and will become important characteristic of the computer in the future.Research in automatic speech recognition by machine has been done for almost four decades. The speech-recognition systems has been developed as an integrated theory, and has been arrived the state of commodity, the basic theory is quite perfect and lots of products come forth in succession, but in many special field, because of the circumstance and the industry, we often need develop the system specially. At present, the accuracy of speech recognition can be satisfactory in quiet circumstance, but with the noise polluting and the circumstance changing, its performance will degrade severely. So a new project of speech recognition in noisy environment is given based on the technology characteristic of speech recognition.The existing major recognition methods of speech recognition system are endpoint detection, pick-up parameters and pattern matching, etc. Based on deeply comprehension in the fundamentals of speech recognition, some major improvements have been made: the first improvement is about pick-up parameters of speech signal. Two improved methods of pick-up parameters are presented: One-Sided Autocorrelation LPC and LPC Prediction Error. On the basis of certification that the two methods have better resistance to noise than traditional LPC method, difference of these two methods is presented. The second is that based on traditional DTW speech recognition, the system can recognize and respond quickly by limiting route’s slope and improving some route, especially when applied in small vocabulary speech recognition and speaker-dependent recognition.This improved algorithm of speech recognition has been realized by C language and simulated on PC, and the result has been given. The experimental result indicates that, compared with traditional speech recognition system, the improved speech recognition system can overcome noisy interference effectively, reduce or eliminate mismatch between training model and testing voice, and Improve systemic response rate. Theoretical analysis and simulation experiments data in the environment of noise is provided in my paper.

Related Dissertations

  1. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34
  2. The Design of a DSP-Based Robot Speech Command Recgnition System,TN912.34
  3. The Design and Research of Health Management Based on Smartphone Environment,TN929.53
  4. Mobile audio and video interactive platform of business execution,TN915.09
  5. Power spectrum estimation in the broadband ADCP Signal Detection Research and Application,TN911.23
  6. Telephone-based channel voiceprint recognition algorithm,TN912.34
  7. Research on Hmm-based Speech Recognition System of the Robot,TN912.34
  8. A Music Retrieval System Base on Humming,TN912.3
  9. MFCC -based speech recognition system to improve research and design,TN912.34
  10. Robot Control System Simulation,TP242
  11. Research and Implemenation of Voice Intelligent plantform Based on VoiceXML,TP311.52
  12. Topic Classification of Speech Documents Based on the Word Fragment Network,TN912.3
  13. Study on Hybrid Model of Speech Recognition Based on HMM and PNN,TN912.34
  14. Mobile robot voice recognition control simulation system design and implementation,TN912.34
  15. Research on Endpoint Detection Algorithm and Implementation in Hardware,TN912.34
  16. Research on DBN-Based Continuous Speech Recognition,TN912.34
  17. STRAIGHT spectrum - based speech recognition algorithm research,TN912.34
  18. Endpoint Detection of Speech Signal Based on Empirical Mode Decomposition,TN912.3
  19. Design and Implementation of Speaker Recognition System Based on Windows CE,TN912.34
  20. Research on the Key Technologies fo Speech Recognition for Robot Communication,TN912.34
  21. The LVCSR system based on adaptive methods of semi-supervised learning,TN912.34

CLC: > Industrial Technology > Radio electronics, telecommunications technology > Communicate > Electro-acoustic technology and speech signal processing > Speech Signal Processing > Speech Recognition and equipment
© 2012 www.DissertationTopic.Net  Mobile