Dissertation > Excellent graduate degree dissertation topics show

A Study of Speech Features Extraction and Matching Algorithm under Noisy Conditions

Author: HanWeiSheng
Tutor: LiuWei
School: Henan University of Science and Technology
Course: Control Theory and Control Engineering
Keywords: Speech recognition Speech Enhancement Feature Extraction Dynamic time Reformed Hidden Markov Models
CLC: TN912.34
Type: Master's thesis
Year: 2011
Downloads: 100
Quote: 0
Read: Download Dissertation

Abstract


Speech recognition is an important research direction of the voice signal processing , and its purpose is to achieve a barrier-free communication between man and machine . Current speech recognition systems under test conditions can usually obtain excellent results , but when applied to actual performance will suddenly dropped . This thesis is to improve the performance of speech recognition systems were explored key technologies with a focus on the technology of speech recognition in noisy environments . The paper first introduces the basic overview of speech recognition , description of research significance , and speech recognition principle is analyzed ; research papers on speech enhancement algorithm for the lower rate of speech recognition in a noisy environment , to analyze a few kinds of commonly used speech enhancement algorithms : spectral subtraction , adaptive offset method , wavelet threshold method is proposed based on the Hilbert-Huang transform speech enhancement method based on empirical mode decomposition different basis function component , adaptive regulator the threshold to achieve de-noising , simulation experiments illustrate the advantages of the method . Next, the paper analyzes the characteristic parameter extraction algorithm , summarized and analyzed several more popular feature parameter extraction algorithm , linear prediction coefficients , perceptual linear cepstral coefficients and Mel frequency cepstrum principle processes made detail the pros and cons of these types of trials comparing coefficient . The last research papers in the voice recognition matching algorithm , introduced three matching algorithm : vector quantization , dynamic time Reformed technology and hidden Markov models . The first two techniques in isolated words , small vocabulary speech recognition systems have achieved good results , but the hidden Markov model advantages in large vocabulary continuous speech recognition system . Overburdened problem for large vocabulary speech recognition , the Viterbi algorithm with Beam pruning techniques combine basic recognition rate affected greatly compresses the search space , reducing the computational burden , and propose a optimize the the pruning threshold test to prove the feasibility of the method .

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Multiple ANN/HMM Hybrid Used in Speech Recognition,TN912.34
  3. The Design of a DSP-Based Robot Speech Command Recgnition System,TN912.34
  4. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  5. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  6. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  7. Multi-currency Notes Technology Research and Implementation,TP391.41
  8. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  9. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  10. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  11. The Research of Image Matching Method Based on Feature Descriptor,TP391.41
  12. Research on Multiple Moving Objects Classification from Video,TP391.41
  13. Research and Implementation on Multi-angle Face Detection Technology Based on Continuous Adaboost Algorithm,TP391.41
  14. Based on sparse representation of high spatial resolution remote sensing image texture description Method,TP751
  15. Natural classroom face recognition system based on video streaming Research and Implementation,TP391.41
  16. Intelligent Analysis and Implement of Compliant Information Based on Filter Technology,TP391.1
  17. Study on Cnc Manufacturing-oriented Key 3d Portrait Modeling Technology and Its Application,TP391.41
  18. Research on Face Recognition Based on Improved Maximum Margin Criterion,TP391.41
  19. Cobalt crusts nonlinear ultrasound identification technology,TN912.34
  20. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  21. Research on Speaker Recognition System under the Visual C++ 6.0,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