基于功率谱特征的音频指纹实现  

Realization of audio fingerprint based on power spectrum feature

作　　者：鲁明明[1] 张晖[1] 沈庆宏[1] Lu Mingming Zhang Hui Shen Qinghong(School of Electronics Science and Engineering, Nanjing University, Nanjing 210046,China)

机构地区：[1]南京大学电子科学与工程学院,南京210046

出　　处：《电子测量技术》2016年第9期69-72,共4页Electronic Measurement Technology

摘　　要：音频指纹是指一段可以表示音频信号重要声学特征的摘要,在音频信号的识别、安全验证、完整性校验等方面有广泛的用途。提出了一种基于信号功率谱特征的音频指纹编码方法,通过对音频信号做STFT计算功率谱,提取信号时频域的功率极值点作为特征并利用其空间结构做哈希计算得到音频指纹。经过实验验证,该算法对时长为2s以上的音频样本可以达到95%以上的识别率,对AWGN噪声具有较强的抑制能力,具有算法简单、识别快速准确、鲁棒性高、抗噪声能力强等特点。Audio fingerprint is a digital digest of the signal which represents the most significant characteristics and is widely used in identification、security validation and integrity verification of audio signal .This paper presents a method of generating audio fingerprint based on the power spectrum characteristics of the signal .After calculating STFT of the input sample and extracting the peak of the power spectrum ,we use the space structure of the peaks as input of the hash function of the audio fingerprint algorithm .As experiment shows ,it could achieve a recognition accuracy of over 95% when the audio sample lasts more than 2 s and shows good resistance to AWGN noise .It is easy to implement、robust enough and exhibits fast and accurate identification ability .

关 键 词：音频指纹 短时傅里叶变换 峰值滤波 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]