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