Dissertation > Excellent graduate degree dissertation topics show

Research on Mandarin Connected Digit Speech Recognition System Based on HTK

Author: JiangZhengFeng
Tutor: HuangHanMing
School: Guangxi Normal University
Course: Computer Software and Theory
Keywords: Speech recognition Hidden Markov Model Hidden Markov Toolbox Mel cepstral coefficients
CLC: TN912.34
Type: Master's thesis
Year: 2009
Downloads: 170
Quote: 2
Read: Download Dissertation

Abstract


With the development of computer and information technology continue to voice interactive technology will become a necessary means of human-computer interaction . Speech recognition technology is to allow machines to understand human speech and perform related actions , is a research hotspot . Continuous digital speech recognition is an important branch of speech recognition , it has broad application prospects in reality , the Internet , communications , military , defense , human-computer interaction , has important application value . Although a lot of research in this area , but there are still many issues to be explored further. This paper is based on HTK Chinese continuous digit recognition and research analysis , first on HTK (Hidden Markov Model Toolkit) software architecture and HTK toolkit to build out based the HTK the Chinese continuous digital speech recognition system , test acoustic models , Gaussian mixture components and MFCC dimension system recognition rate . Then, in the understanding based on the HTK speech recognition system structures on the basis of the process , based on the the HTK voice dialing system , the phone numbers and names of voice recognition . Then , a preliminary study based on the ATK (API of HTK) real-time speech recognition . Discussion of the process , and set up a real - time speech recognition system using ATK ATK - based real-time voice dialing system , but the recognition result is not satisfactory . More complex speech recognition network to carry out the study of the the HTK speech-recognition network to export an optimized speech recognition network , and proved theoretically and experimentally verify its correctness . Finally, the characteristics of speech recognition and Internet transmission technology , design a simple network transmission of voice recognition program : the client / server model to extract the characteristic parameters of the voice signal on the client using the TCP protocol to the characteristic parameters of the transmission to the server by server to complete the work of identifying and training . System using HTK and Visual C programming tools , the use of class encapsulates the Windows Sockets in MFC speech features and network transmission of the recognition results , a preliminary continuous digital speech recognition system based on network transmission .

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. Packet Loss Recovering Technology for Speech Transmission over Network,TN912.3
  4. The Design and Research of Health Management Based on Smartphone Environment,TN929.53
  5. Multi-threaded fusion soccer video semantic analysis and event detection,TP391.41
  6. A Design of Intelligent Terminal of Voice Control Based on ARM9,TN912.3
  7. Research on Anti-noise Speech Recognition Methods Based on Robustness PLPC,TN912.34
  8. FPGA-based speech recognition system design and implementation,TN912.34
  9. A Study of Speech Enhancement and Recognition Based on Microphone Array Processing,TN912.35
  10. Chinese Speech Synthesis System Improvement and Implementation,TN912.33
  11. Study on Speech Recognition Key Technologies and the Realization of the System,TN912.34
  12. Voice-based control of the electric car design,TP273
  13. Research of Speech Recognition of Isolated Word Under Embedded Linux Operation,TN912.34
  14. RBF neural network optimized for speech recognition research,TN912.34
  15. Conjunction speech recognition system codebook design and modeling hardware identification module,TN912.34
  16. Research and Emplementation of Embedded GUI Based on Qt/Embedded and Qtopia,TP368.12
  17. Database System and Tool Wear Monitoring Technology in Plunge Milling,TP311.13
  18. PDF417 two-dimensional bar code identification technology and its implementation in the Linux platform,TP391.44
  19. Embedded wireless Bluetooth-based video acquisition system hardware design and improvement,TP274.2
  20. Research and Realization of Embedded Speaker Independent Continuous English Speech Recognition Based on HMM,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