基于貝葉斯網(wǎng)絡(luò)的語音情感識別
本文選題:語音情感識別 切入點(diǎn):貝葉斯網(wǎng)絡(luò) 出處:《華南理工大學(xué)》2014年碩士論文 論文類型:學(xué)位論文
【摘要】:情感識別的目的是讓計(jì)算機(jī)能讀懂人的情感,進(jìn)而表達(dá)出情感,使實(shí)現(xiàn)能理解和表達(dá)人類情感的機(jī)器成為可能。計(jì)算機(jī)的語音情感識別能力是計(jì)算機(jī)情感智能的重要組成部分,是實(shí)現(xiàn)自然人機(jī)交互界面的關(guān)鍵前提,具有很大的研究價(jià)值和應(yīng)用價(jià)值。目前,語音情感識別研究工作主要集中在語音信號預(yù)處理、語音情感特征提取、特征向量降維、語音情感識別算法等方面。 貝葉斯網(wǎng)絡(luò)是1988年由Pearl提出的一種在貝葉斯決策方法的基礎(chǔ)上發(fā)展起來的一種統(tǒng)計(jì)推斷方法。貝葉斯網(wǎng)絡(luò)以獨(dú)特的不確定性知識表達(dá)形式、豐富的概率表達(dá)能力、綜合先驗(yàn)知識的增量學(xué)習(xí)特性成為近幾年來理論研究的熱點(diǎn),,被廣泛應(yīng)用于輔助智能決策、模式識別、醫(yī)療診斷等領(lǐng)域。 本文選取語音情感識別算法作為重點(diǎn)的研究方向,提出了將基本分類器結(jié)合貝葉斯網(wǎng)絡(luò)應(yīng)用到語音情感識別中。通過對貝葉斯網(wǎng)絡(luò)進(jìn)行了深入的研究,提出使用貝葉斯網(wǎng)絡(luò)對基本分類器分類結(jié)果進(jìn)行調(diào)整,并且提出了基于混淆矩陣的貝葉斯網(wǎng)絡(luò)生成算法,并將本文改進(jìn)的算法應(yīng)用到語音情感識別的研究中,分別使用支持向量機(jī)SVM和樸素貝葉斯NB為基本分類器,使用貝葉斯網(wǎng)絡(luò)調(diào)整分類結(jié)果,在語音情感數(shù)據(jù)庫(Berlin、CASIA、SAVEE)做了實(shí)驗(yàn),獲得比原來算法更好的分類準(zhǔn)確率。
[Abstract]:Emotion recognition is to let computer can understand people's feelings, and express feelings, make to understand and express human emotion machine possible. Speech emotion recognition ability of the computer is an important part of emotional intelligence, is a key prerequisite to achieve mutual natural human-computer interface, has great research value and application value. At present, the speech emotion recognition research focuses on speech signal preprocessing, speech feature extraction, dimensionality, speech emotion recognition algorithm.
Bias network is a statistical method to develop a decision-making method based on Bias proposed in 1988 by Pearl on the network. Bias with unique uncertain knowledge expression, rich probability expression ability, comprehensive incremental prior knowledge of the learning characteristics in recent years become the focus of theoretical research, is widely used in intelligence decision-making, pattern recognition, medical diagnosis and so on.
This paper selects the speech emotion recognition algorithm as the research focus, puts forward the basic combination of Bayesian network classifier is applied to speech emotion recognition. Based on Bayesian networks is studied, using Bayesian network to adjust the basic classification results, and proposed a Bayesian network generation algorithm based on confusion matrix, and the the improved algorithm is applied to the study on the speech emotion recognition, using support vector machine SVM and Naive Bayesian NB as the basic classifier, Bayesian network is used to adjust the results of classification in speech emotion database (Berlin, CASIA, SAVEE) to do the experiment, obtained better than the original algorithm classification accuracy.
【學(xué)位授予單位】:華南理工大學(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7條
1 林奕琳;韋崗;楊康才;;語音情感識別的研究進(jìn)展[J];電路與系統(tǒng)學(xué)報(bào);2007年01期
2 孔英會;景美麗;;基于混淆矩陣和集成學(xué)習(xí)的分類方法研究[J];計(jì)算機(jī)工程與科學(xué);2012年06期
3 余伶俐;周開軍;邱愛兵;;基于Elman神經(jīng)網(wǎng)絡(luò)的語音情感識別應(yīng)用研究[J];計(jì)算機(jī)應(yīng)用研究;2012年05期
4 胡春玲;胡學(xué)鋼;姚宏亮;;改進(jìn)的基于鄰接樹的貝葉斯網(wǎng)絡(luò)推理算法[J];模式識別與人工智能;2011年06期
5 胡春玲;;貝葉斯網(wǎng)絡(luò)研究綜述[J];合肥學(xué)院學(xué)報(bào)(自然科學(xué)版);2013年01期
6 胡云安;劉振;宋瑞華;史建國;;爬山法與模式蟻群法混合的貝葉斯優(yōu)化算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年05期
7 張振海;王曉明;黨建武;閔永智;;基于專家知識融合的貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)方法[J];計(jì)算機(jī)工程與應(yīng)用;2014年02期
本文編號:1605594
本文鏈接:http://sikaile.net/kejilunwen/wltx/1605594.html