聲紋識別系統(tǒng)關(guān)鍵技術(shù)研究
發(fā)布時間:2018-03-11 13:33
本文選題:聲紋識別 切入點:特征提取 出處:《哈爾濱理工大學(xué)》2014年碩士論文 論文類型:學(xué)位論文
【摘要】:聲紋如同指紋、人臉一樣,是人體特有的一種生物特征。由于其方便性和經(jīng)濟(jì)性,聲紋識別作為生物認(rèn)證技術(shù)的一種,逐漸走入大眾的視線。聲紋識別不同于語音識別,顧名思義,聲紋識別注重的是待識別的語音信號中說話人的聲紋特征,無需知道說話內(nèi)容。由于每個人都有其獨一無二的聲紋特征,很難被模仿偽造,因此,相對于其他生物認(rèn)證技術(shù),聲紋識別技術(shù)在身份認(rèn)證領(lǐng)域更加地安全、可靠。 本文主要是對與文本無關(guān)的聲紋識別系統(tǒng)的關(guān)鍵技術(shù)進(jìn)行研究,力圖在前人研究的基礎(chǔ)上有所創(chuàng)新,以提高系統(tǒng)的識別率。首先在宏觀上分析了聲紋識別的課題背景、發(fā)展現(xiàn)狀及研究難點等,并對聲紋識別系統(tǒng)的結(jié)構(gòu)原理進(jìn)行介紹,其次分析了聲紋識別系統(tǒng)的端點檢測部分,,然后重點對聲紋識別的關(guān)鍵部分特征提取模塊進(jìn)行研究。主要包括分析聲紋識別系統(tǒng)的特征提取模塊中線性預(yù)測倒譜系數(shù)(Linear Prediction Cepstrum Coefficient,LPCC)與Mel頻率倒譜系數(shù)(Mel Frequency Cepstrum Coefficient,MFCC)的提取原理,并對MFCC參數(shù)的提取進(jìn)行了改進(jìn),提出了基于小波變換和改進(jìn)的MFCC參數(shù)組合特征的提取算法。最后用高斯混合模型通過實驗的方式對特征提取部分的不同算法進(jìn)行分析比較,達(dá)到了提高了系統(tǒng)的效率的目的。
[Abstract]:Sound pattern, like fingerprint and face, is a special biological feature of human body. Because of its convenience and economy, sound pattern recognition, as a kind of biometric authentication technology, has gradually come into the public's sight. Voice pattern recognition is different from speech recognition. As the name implies, voice-pattern recognition focuses on the speaker's voice-pattern feature in the speech signal to be recognized, without knowing what to say. Because everyone has its unique voice-pattern feature, it is difficult to imitate and forge, so, Compared with other biometric authentication technologies, voiceprint recognition technology is more secure and reliable in the field of identity authentication. This paper mainly studies the key technology of text-independent voiceprint recognition system, and tries to innovate on the basis of previous research in order to improve the recognition rate of the system. This paper introduces the structure principle of the voiceprint recognition system, and then analyzes the endpoint detection part of the voiceprint recognition system. Then the key part of feature extraction module of sound stripe recognition is studied, including the principle of linear predictive cepstrum coefficient (linear Prediction Cepstrum coefficient) and Mel frequency cepstrum coefficient (Mel Frequency Cepstrum efficient Prediction) in the feature extraction module of sound stripe recognition system, and the principle of linear predictive cepstrum coefficient (LPC) and Mel frequency cepstrum coefficient (Mel Frequency Cepstrum efficient Prediction) are analyzed. After improving the extraction of MFCC parameters, an algorithm based on wavelet transform and improved MFCC parameter combination feature extraction is proposed. Finally, the different algorithms of feature extraction part are analyzed and compared by using Gao Si mixed model through experiments. The efficiency of the system is improved.
【學(xué)位授予單位】:哈爾濱理工大學(xué)
【學(xué)位級別】:碩士
【學(xué)位授予年份】:2014
【分類號】:TN912.34
【參考文獻(xiàn)】
相關(guān)期刊論文 前8條
1 黃成玉;張全柱;賴斌;;聲紋識別中MEL參數(shù)的提取研究[J];電源技術(shù);2011年04期
2 葉田田;;聲紋識別系統(tǒng)設(shè)計[J];工業(yè)控制計算機(jī);2012年06期
3 潘丹青;戴憲華;潘矜矜;;一種高效語音基音檢測方法的研究[J];測控技術(shù);2010年07期
4 張君昌;李艷艷;;基于小波變換的魯棒性語音特征提取新方法[J];計算機(jī)仿真;2010年08期
5 趙臘生;張強(qiáng);魏小鵬;;語音情感識別研究進(jìn)展[J];計算機(jī)應(yīng)用研究;2009年02期
6 王娜;;基于MFCC的語音評分方法研究[J];中國現(xiàn)代教育裝備;2010年15期
7 林瑋;楊莉莉;徐柏齡;;基于修正MFCC參數(shù)漢語耳語音的話者識別[J];南京大學(xué)學(xué)報(自然科學(xué)版);2006年01期
8 朱青松;崔健;王凱;李勇;;動態(tài)閾值雙門限語音端點檢測研究[J];科技創(chuàng)新導(dǎo)報;2009年14期
本文編號:1598391
本文鏈接:http://sikaile.net/kejilunwen/wltx/1598391.html
最近更新
教材專著