Dissertation > Excellent graduate degree dissertation topics show
Design of Access Control System Based on Speaker Recongnition
Author: WeiGuoTeng
Tutor: JiaLiang
School: Shenyang Institute of Aeronautical College
Course: Signal and Information Processing
Keywords: Speaker Recognition Access Control System TMS320VC5509 Mel cepstrum Vector quantization
CLC: TP273.5
Type: Master's thesis
Year: 2010
Downloads: 118
Quote: 1
Read: Download Dissertation
Abstract
|
Speaker recognition technology developed in recent years , computer security technology . Also known as voiceprint recognition, speaker recognition based on the characteristics of the speaker's voice , speaking habits and personality traits to identify different speakers . With the rapid development of society , it is widely used in the areas of attendance system , security control and financial security . The content of this article is to study the text independent speaker recognition algorithm and achieve the algorithm access control system on the DSP . This article 's speaker recognition algorithm with the United States and Seoul cepstrum parameters and vector quantization . Fully consider the characteristics of human hearing Simmel cepstrum parameters used for the selection of characteristic parameters . This selection of vector quantization , vector quantization is a very high efficiency coding techniques for pattern matching techniques , . When a small amount of data that can be used for training , the method based on vector quantization greater robustness than other methods . At the same time , based on vector quantization method is relatively simple, real-time is also good . Therefore , until now , speaker recognition method based on vector quantization , is still one of the most commonly used identification methods . Contrast, speaker recognition based on dynamic time warping and vector quantization in Matlab environment derived from the experimental results of the vector quantization technique for text-independent speaker recognition better dynamic time warping , so the pattern matching technology selected vector quantization . For the realization of the access control system , the entire system includes three parts, the acquisition of the voice , the voice signal storage, and related information is displayed . The hardware mainly based on TI's digital signal processor TMS320VC5509, audio codec TLV320AIC23, off-chip SDRAM memory chips and liquid crystal display modules. Work on this basis : use TLV320AIC23 voice signal acquisition ; digital voice signal will be collected through the McBSP send TMS320VC5509 ; voice signal characteristic parameter extraction and its recognition algorithm in TMS320VC5509 on achieve ; identifiable end LCD screen display, and to issue the corresponding control command .
|
Related Dissertations
- A Design Study of PLC Elevator Access Control System Based on RFID,TP273.5
- Speaker Recognition Based on SOPC controller,TN912.34
- Auditory System Property about Speech Signal Process,TN912.3
- Complex channel speaker recognition technology,TN912.34
- Research on Speaker Recognition System under the Visual C++ 6.0,TN912.34
- Mixing characteristics and Gaussian mixture model - based speaker recognition,TN912.34
- Design and Implementation of Speaker Recognition System Based on Windows CE,TN912.34
- Study of Extraction and Optimization Characteristic Parameters in Speaker Recognition,TN912.34
- The Research Based on the Text Irrelevant Speaker Distinguishes,TN912.34
- G.729 voice codec algorithm and its DSP implementation,TN919.81
- Research and Implementation on Real-time Speaker Recognition Algorithmin in Multiplexing Parallel Model,TN912.34
- Design and Implementation of the fingerprint identification and radio frequency ( RF ) technology in the prison in the access control system,TP273.5
- The Development of Speaker Recognition System Based on Support Vector Machine,TN912.34
- Research on Text-independence of Open-set Speaker Recognition,TN912.34
- Speaker Recognition Research in Noisy Environment,TN912.34
- EMD-based speaker recognition,TN912.34
- Rapid Speaker Recognition Based on GMM-UBM,TN912.34
- Research on Real-Time Audio Decoding and Robust Speaker Recognition System in Network Environment,TN912.34
- Research of Text Dependent Speaker Recogniton on Embedded System,TN912.34
- Speaker Recognition on the Base of Time-Varying Characteristics of Speech Signal,TN912.34
- Speaker Identification in Chinese Whispered Speech Based on Simplified Joint Factor Analysis,TN912.34
CLC: > Industrial Technology > Automation technology,computer technology > Automation technology and equipment > Automation systems > Automatic control,automatic control system > Computer control, computer control system
© 2012 www.DissertationTopic.Net Mobile
|