基于MFCC的語音情感特征提取研究
發(fā)布時間：2018-07-25 13:34
【摘要】：為了研究"世界記憶遺產(chǎn)"東巴經(jīng)典古籍的音頻分類,以通過語音情感特征提取的方法分類鑒別東巴音頻類別,并實現(xiàn)對東巴經(jīng)典語音的情感狀態(tài)識別,同時提高人機交互性能,提出采用Mel頻率倒譜系數(shù)(MFCC)實現(xiàn)語音情感特征的提取。通過引入MFCC的一階差分、二階差分描述語音特征的動態(tài)特征,并整合短時能量特征,最終形成MFCC和短時能量相疊加的語音信號特征參數(shù),達到提取反映語音情感特征的目的。實驗驗證表明,該語音信號特征提取方法能夠更明顯地區(qū)分出包含在語音中的情感信息,為語音情感特征的識別研究及東巴古籍音頻分類鑒別提供理論基礎。
[Abstract]:In order to study the audio classification of the classic ancient books of the "World Memory Heritage" of Dongba, the audio classification of Dongba was identified by the method of speech emotion feature extraction, and the emotional state recognition of the classic voice of Dongba was realized and the human computer interaction performance was improved. The Mel frequency cepstrum coefficient (MFCC) was used to extract the emotion feature of the speech. After introducing the first order difference of MFCC, the two order difference describes the dynamic characteristics of the speech feature, and integrates the short time energy characteristics, and finally forms the feature parameters of the speech signal which is superimposed by the MFCC and the short-time energy, and achieves the purpose of extracting the emotional characteristics of the speech. The experimental verification shows that the speech signal feature extraction method can be more clearly divided in the region. The emotion information contained in speech provides a theoretical basis for the recognition of speech emotion characteristics and the audio classification and identification of Dongba ancient books.
【作者單位】： 北京信息科技大學機電學院;中央民族大學;麗江東巴文化研究院;
【基金】：國家社科基金重大項目(12&ZD234) 現(xiàn)代測控技術教育部重點實驗室開放課題(KF20161123205) 北京市重點實驗室開放課題(KF20161123208)資助項目
【分類號】：TN912.3
本文編號：2143981
[Abstract]:In order to study the audio classification of the classic ancient books of the "World Memory Heritage" of Dongba, the audio classification of Dongba was identified by the method of speech emotion feature extraction, and the emotional state recognition of the classic voice of Dongba was realized and the human computer interaction performance was improved. The Mel frequency cepstrum coefficient (MFCC) was used to extract the emotion feature of the speech. After introducing the first order difference of MFCC, the two order difference describes the dynamic characteristics of the speech feature, and integrates the short time energy characteristics, and finally forms the feature parameters of the speech signal which is superimposed by the MFCC and the short-time energy, and achieves the purpose of extracting the emotional characteristics of the speech. The experimental verification shows that the speech signal feature extraction method can be more clearly divided in the region. The emotion information contained in speech provides a theoretical basis for the recognition of speech emotion characteristics and the audio classification and identification of Dongba ancient books.
【作者單位】： 北京信息科技大學機電學院;中央民族大學;麗江東巴文化研究院;
【基金】：國家社科基金重大項目(12&ZD234) 現(xiàn)代測控技術教育部重點實驗室開放課題(KF20161123205) 北京市重點實驗室開放課題(KF20161123208)資助項目
【分類號】：TN912.3
【相似文獻】
相關期刊論文 前9條
1 張偉偉;楊鼎才;;用于說話人識別的MFCC的改進算法[J];電子測量技術;2009年08期
2 王偉;鄧輝文;;基于MFCC參數(shù)和VQ的說話人識別系統(tǒng)[J];儀器儀表學報;2006年S3期
3 肖漢光;何為;;基于MFCC和SVM的說話人性別識別[J];重慶大學學報;2009年07期
4 蔣永生;張雄偉;閔剛;劉光云;陳功;;基于改進的MFCC戰(zhàn)場被動聲目標識別[J];彈箭與制導學報;2008年06期
5 李霄寒,戴蓓倩,方紹武,劉鳴;高階MFCC的話者識別性能及其噪聲魯棒性[J];信號處理;2001年02期
6 韓春光;李華;;提高MFCC魯棒性的方法[J];計算機工程與設計;2008年01期
7 陳月朝;付卓;劉宏;;基于LLR融合基頻與MFCC的說話人性別識別[J];華中科技大學學報(自然科學版);2013年S1期
8 陳迪;龔衛(wèi)國;李波;;噪聲魯棒性說話人識別語音高頻加權MFCC提取[J];儀器儀表學報;2008年03期
9 ;[J];;年期
相關碩士學位論文 前2條
1 于艷山;基于MFCC與VQ碼本的不良音頻檢測算法研究[D];蘭州大學;2015年
2 姜龍生;基于MFCC和小波包變換及模糊SVM的飛機艙音識別[D];南京航空航天大學;2011年
，本文編號：2143981
本文鏈接：http://sikaile.net/kejilunwen/xinxigongchenglunwen/2143981.html
最近更新
教材專著
