基于改進(jìn)小波包變換的音頻指紋提取算法

朱　潔,鄧開發(fā)

(1.上海理工大學(xué) 光電信息與計(jì)算機(jī)工程學(xué)院,上海　200093;2.上海工程技術(shù)大學(xué) 藝術(shù)設(shè)計(jì)學(xué)院,上海　200093)

?

基于改進(jìn)小波包變換的音頻指紋提取算法

朱潔1,鄧開發(fā)2

(1.上海理工大學(xué) 光電信息與計(jì)算機(jī)工程學(xué)院,上海200093;2.上海工程技術(shù)大學(xué) 藝術(shù)設(shè)計(jì)學(xué)院,上海200093)

摘要數(shù)字音頻指紋技術(shù)在音頻信號分析和處理中起著重要作用。針對傳統(tǒng)基于時(shí)頻分析的音頻指紋提取算法中僅使用信號能量作為特征參數(shù),而無法全面表征出信號的復(fù)雜度和不規(guī)則性問題,提出了基于小波包分解與重構(gòu),將小波包系數(shù)的奇異值熵和樣本熵相結(jié)合,作為音頻信號的特征參數(shù)提取指紋。實(shí)驗(yàn)證明,該算法提取的指紋提高了音頻識別的準(zhǔn)確率,在常見信號處理下能保持較強(qiáng)的魯棒性,并具有明顯的區(qū)分音頻和定位音頻篡改位置的能力。

關(guān)鍵詞音頻指紋;小波包分解;奇異值熵;樣本熵;特征提取

An Approach to Audio Fingerprinting Extraction Based on Improved Wavelet Packet

ZHU Jie1,DENG Kaifa2

(1.School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;2.School of Art and Design,Shanghai University of Engineering Science,Shanghai 201620,China)

AbstractDigital audio fingerprinting technology plays an important role in the audio analysis and processing.Aiming at the problem that the traditional audio fingerprinting is extracted based on time frequency analysis using the energy of signal as a single feature parameter that can not fully characterize the complexity and irregularity,the paper proposes a method for audio fingerprinting extraction based on wavelet packet decomposition and reconstruction and combining the sample entropy of wavelet packet coefficients and the entropy singular value as a signal characteristic parameters to extract audio fingerprinting.Experimental results show that the proposed algorithm is accurate in audio recognition,robust in common audio signal operations,and capable of distinguishing different audio and locate tampered position.

Keywordsaudio fingerprinting;wavelet packet decomposes;entropy of singular values;sample entropy;feature extraction

近年來,基于內(nèi)容的音頻檢索(Content-Based Audio Retrieval,CBAR)技術(shù)出現(xiàn)了許多新的研究和發(fā)展方向,而音頻指紋(Audio Fingerprinting,AF)技術(shù)是 CBAR 的關(guān)鍵技術(shù)之一,其主要目的是建立一種有效機(jī)制來比較兩個(gè)音頻數(shù)據(jù)的聽覺質(zhì)量,是從音頻中提取的具有音頻聲學(xué)特征的緊致數(shù)字簽名。AF基金項(xiàng)目:南京市領(lǐng)軍型科技創(chuàng)業(yè)人才引進(jìn)計(jì)劃基金資助項(xiàng)目(No.2014A090002)技術(shù)在數(shù)字音頻內(nèi)容的音頻內(nèi)容識別、版權(quán)保護(hù)、內(nèi)容完整性校驗(yàn)等領(lǐng)域都具有廣泛的應(yīng)用價(jià)值,逐漸成為國內(nèi)外學(xué)者研究的熱點(diǎn)。

學(xué)術(shù)界對音頻指紋技術(shù)的研究主要包括基于時(shí)域音頻指紋算法、頻域音頻指紋算法和時(shí)頻域音頻指紋算法[1]。……