本科毕业设计—基于声纹的说话人特征识别.docVIP

JIU JIANG UNIVERSITY 毕 业 论 文（设 计） 题 目 基于声纹的说话人特征识别 英文题目 Speaker feature recognition based on the voiceprint 院 系 专 业 姓 名 年 级 指导教师 2013年6月 摘 要 说话人识别是一项根据语音波形中反映说话人生理和行为特征的语音参数，而自动识别说话人身份的技术。它也常被人们称为声纹识别技术，是生物认证技术的一种，其基本思想就是运用某种匹配方法进行特征识别，从而确定说话人的身份。 目前已知的语音特征包括基音周期、语谱图、自相关系数、能量、平均幅度、过零率、共振峰、线谱对、线性预测系数（LPC）、线性预测倒谱（LPCC）、Mel频率倒谱（MFCC）等。 本文介绍了说话人识别的概念、原理及其识别实现的方法，指出了说话人识别技术的应用前景。通过在Matlab7.0平台上对语音的基音周期、线性预测倒谱和Mel频率倒谱等特征参数进行提取、分析、对比、识别实现一个简单的说话人识别系统，实验结果表明实验正确、有效。 关键字：说话人识别；特征参数；基音周期；线性预测倒谱；Mel频率倒谱 Speaker feature recognition based on the voiceprint Abstract Speaker recognition is the voice parameters in a speech waveform which reflects the speakers physiological and behavioral characteristics, and automatic identification technology to speaker identity. It is also often referred to as the voiceprint recognition technology, a biometric authentication technology.The basic idea is to use a matching method for feature recognition, in order to determine the identity of the speaker.  Currently known voice features include pitch, spectrogram, since the correlation coefficient, energy, average magnitude, the zero crossing rate, formant, the line spectrum of the Linear Prediction Coefficient (LPC), Linear Prediction Cepstrum (LPCC) , Mel Frequency Cepstral (MFCC).  This article describes the speaker identification concepts, principles and implementation methods of identification, and pointed out the prospect of speaker recognition technology. By the Matlab7.0 platform, voice pitch, linear prediction cepstrum and Mel Frequency inverted spectra characteristic parameter extraction, analysis, contrast, identify a simple speaker recognition system, experimental results show that the experiment is correct, effective .