Speaker Recogniton Based on
MFCC and Neural Network Array
(English:作者第一、第二、第三)
(1学校、学院 省份 市 邮编 2、学校、学院 省份 市 邮编)
Abstract:Speaker Recognition is a popular subject,also many speaker recognition methods are used . In this paper, the popular Mel cepstrum coefficients and neural networks are used to build a speaker recognition system. Characteristics of human hearing based on MFCC parameters, can better reflect the characteristics of pitch based on sound physiological profile and the rate of change of pitch period. Neural network has good flexibility and scalability, can simulate any nonlinear system, especially in the recognition of non-specific people, the specific people’s voice model can also be extracted from a large number of voice data. Experiments show that: This article uses the speaker recognition model, The recognition rate can reach 96% With good recognition.
Key Words: speaker recognition, Mel Cepstrum coefficient, Neural array Network
Joseph P,Campbell. Speaker Recognition :A Tutorial. [J]. Proceedings of the IEEE ,1997,85(9):1437-1462
Hermansky H. Perceptual Linear Prediction(PLP) Analysis for Speech[J],JASA,1990,1738-1752
Huang,Jong Tai-Langl,Hsieh,Chi-Yi,The prompt of lip shape modification of cacology based on the speech evaluation techniques-A case of basic Chinese learining. 2008
Preprocessing Techniques for Voice-Print Analysis for Speaker Recognition, Dzati Athiar RamliSalina Abdul SamadAini Hussain, 5th Student Conference on Research and Development (SCOReD 2007), 2007
Security System Using Biometric Technology: Design and Implementation of Voice Recognition System (VRS) , Rozeha A. RashidNur Hija MahalinMohd Adib SarijariAhmad Aizuddin Abdul Aziz, 2008 International Conference on Computer and Communication Engineering (ICCCE 2008), vol.2
Identifying Voice Characteristic Among Various Ethenicities Through Spectrographic Analaysis And Acoustic Pharyngeometry,Randy HetheringtonJason RichmondAudio Engineering Society,d Audio Engineering Society International Conference 2008: "Audio Forensics: Theory and Practice" ,2008
VoizLock - Human Voice Authentication System using Hidden Markov Model, Jayamaha.R.G.Maduranga,MSenadheera,Maduri.R.RGamage,T.Nuwan.CWeerasekara, K.D. Pavithra BDissanayaka, Gayan AKodagoda, G. NuwanICIAFs,Information and Automation for Sustainability,ICIAFs,2008 4th International Conference on; Colombo,Sri Lanka
Voice Recognition System for the Visually Impaired: Virtual Cognitive Approach,Halimah, B. Z.Azlina, A.Behrang, P.Choo, W. O.,3rd International Symposium on Information Technology (ITSim 2008),2008
Comparison of Different Implementations of MFCC,Zheng Fang Zhang Guoliang Song Zhanjiang, Department of Computer Science and Technology, Tsinghua University,Beijing 100084 ,P.R.China
Speech Emotion Verification System (SEVS) Based On MFCC For Real Time Applications, Norhas linda Kamaruddin Abdul Wahab, 4th International Conference on Intelligent Environments (IE 2008)
李晶皎,孙杰等.语音识别中HMM与自组织神经网络混合结合的混合模型【J】.东北大学学报,1999
王金明,张雄伟.基于MFCC和LSP混合的语音特征参数的技术研究【J】.计算机与信息技术,2007
惠博.语音识别特征提取算法的研究及实现【D】.西北大学,2008
王金明,张雄伟.基于MFCC和LSP混合的语音特征参数的技术研究【J】.计算机与信息技术,2007
郭武,戴礼荣,王仁华.结合基音周期与清浊音信息的动态梅尔倒谱参数.数据采集预处理,2007
朱浩冰,郭东辉.声纹识别系统原理及其关键技术.计算机安全,2007
张煜睿,常学义,冯涛.一种改进的LBG算法在声纹识别中的应用.上海第二工业大学学报,2007
杨阳,陈永明.声纹识别技术及其应用.电声技术,2007
殷启新,贾学明,彭宇.数字声纹识别技术在刑侦工作中的应用.计算机技术,2007
吕俊,前馈神经网络参数和结构的优化策略研究 南京:南京工业大学 2004