基于小波變換的語音基頻提取新算法
A new algorithm for pitch detection of speech signals using wavelet transform
-
摘要: 該文將小波變換應(yīng)用于具有連續(xù)語音特征的三字詞語音的基頻提取,并針對實(shí)驗(yàn)中出現(xiàn)的問題對算法進(jìn)行了改進(jìn),提出了一種新的基于小波變換的語音基頻檢測算法。該算法主要包括:離散小波變換計(jì)算、基于投票策略的基頻點(diǎn)選擇和基頻起點(diǎn)確定、基頻檢查、異常點(diǎn)修正、頭尾漏點(diǎn)處理以及基于投票策略的基頻點(diǎn)精確定位。實(shí)驗(yàn)表明,該算法較好地克服了基于小波變換傳統(tǒng)算法的不足,更適合于連續(xù)語音的基頻提取,缺陷是需要較多的計(jì)算時(shí)間,不太適合于實(shí)時(shí)性要求較高的系統(tǒng)。
-
關(guān)鍵詞:
- 小波變換; 基頻檢測; 投票策略; 語音信號
Abstract: In this paper wavelet transform is applied to pitch detection of Chinese trisyllabic word with characteristic of continuous speech, a new algorithm for pitch detection of speech signals using wavelet transform is proposed for the question appearing in pitch extraction. It is made up of the following processes: calculating discrete wavelet transform, selecting pitch points and determining the first pitch point based on voting strategy, checking pitch, modifying abnormal pitch point, processing pitch miss point at the beginning and end of a frame of speech signals, relocation of pitch point based on voting strategy. It has been found that this algorithm is valid, and very suits to process continuous speech. But it needs much time for computation, so it is not suit for real-time system. -
S.Kadambe,G.Faye Boudreaux-Bartels,Application ofthe wavelettransformfor pitch detectionof speech signal,IEEE Trans.on IT.,1992,IT-38(2),917-924.[2]王長富,林志剛,戴蓓倩,張勁松,基于小波變換的語音基音周期檢測,合肥,中國科學(xué)技術(shù)大學(xué)學(xué)報(bào),1995,25(1),47-52.[3]程俊,張璞,戴善榮,易克初,小波變換用于信號突變的檢測,通信學(xué)報(bào),1995,16(3),96-104.[4]S.Mallat,A theory for multiresolutions signal decomposition:wavelet representation,IEEETrans.on PAMI.,1989,PAMI-11(7),674-692.[5]鐘金宏,楊善林,張學(xué)應(yīng),漢語連續(xù)語音三字詞聲調(diào)提取方法研究,合肥,合肥工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版),2000,23(5),710-714.[6]陶維青,徐士林,鐘金宏,漢語三字詞聲調(diào)的模式分析,中文信息學(xué)報(bào),1998,12(3),29-35. -
計(jì)量
- 文章訪問數(shù): 3009
- HTML全文瀏覽量: 155
- PDF下載量: 1118
- 被引次數(shù): 0
下載:
