Dissertation > Excellent graduate degree dissertation topics show

MFCC -based speech recognition system to improve research and design

Author: WenLin
Tutor: XiongHongYun
School: Central South University
Course: Control Theory and Control Engineering
Keywords: Speech Recognition Endpoint Detection Pitch Detection Feature Extraction
CLC: TN912.34
Type: Master's thesis
Year: 2011
Downloads: 238
Quote: 4
Read: Download Dissertation

Abstract


As information science and embedded technology continues to evolve , speech recognition technology research and on a new level. Using modern means of voice recognition technology, can effectively help us to produce , store and retrieve voice signals , which promote the development of far-reaching social . This paper presents a frequency standard based on improved Mel cepstrum (MFCC) algorithm for speech recognition and its embedded hardware design . This paper describes the speech recognition algorithms and implemented . At the beginning of the specific voice recognition before the paper first introduces a number of short-time speech recognition functions, including short-time average energy , short-time average zero-crossing rate , short-term autocorrelation function and short average magnitude difference function . These functions for subsequent speech recognition algorithm to pave the way . Endpoint detection for speech recognition difficult problem , consider the DC component of the speech signal interference and misjudgment tail tone , putting forward an improved two-door method . Voice Recognition for pitch detection problem , this paper proposes an improved loop short average magnitude difference function (AMDF) method . To get the best voice characteristic parameters , the paper on the basis of the conventional MFCC , which improves the high band frequency characteristics , an improved method MFCC . Experimental results show that the improved feature extraction method improves the speech recognition rate. In speech recognition model , the paper introduces the dynamic time warping model (DTW), hidden Markov model (HMM) and artificial neural network model (ANN). Using a DTW model identification , the model algorithm is simple, high recognition rate. In this paper, the hardware design for a detailed description . To a Samsung S3C2440 processor as the core , the processor has a powerful hardware resources. This paper presents a processor and SDRAM, FLASH, serial port , JTAG, power supply, external AD, LCD screen, voiced connection circuit modules . This specific identification algorithm in MATLAB simulation, simulation achieved good results. The results illustrate that these algorithms can be widely used in the field of speech recognition , which is the development of speech recognition technology has a certain role in promoting.

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. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  5. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  6. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  7. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  8. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  9. Research on Visual Measurement for Spacecraft Rendezvous and Approach,TP391.41
  10. Research on the Image Real-Time Acquisition, Storage and Image Processing System,TP391.41
  11. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  12. Multi-currency Notes Technology Research and Implementation,TP391.41
  13. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  14. Pavement Distress Recognition Based on Image,TP391.41
  15. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  16. Research on Fusion Algorithm of Hyper Spectral and High Spatial Resolution Remote Sensing Image,TP751
  17. The Design and Research of Health Management Based on Smartphone Environment,TN929.53
  18. An Approach for Identifying a Plant Resistance Gene Based on the Random Forest,Q943
  19. Tobacco Diseases Auto-Recognition Research Based on Image Processing Technology,S435.72
  20. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  21. Research on Identification System of Cashmere and Wool Fiber,TS101.921

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