A Novel System for Recognizing Recording Devices from Recorded Speech Signals  

作　　者：Yongqiang Bao Qi Shao Xuxu Zhang Jiahui Jiang Yue Xie Tingting Liu Weiye Xu 

机构地区：[1]Nanjing Institute of Technology,Nanjing,211167,China [2]Department of Informatics,University of Leicester,Leicester,LE17RH,UK

出　　处：《Computers, Materials & Continua》2020年第12期2557-2570,共14页计算机、材料和连续体（英文）

基　　金：supported by the Jiangsu University Student Training Program[SJCX19_0529];the research fund of Nanjing Institute of Engineering[CXY201931];the National Natural Science Foundation of China(61871213).

摘　　要：The field of digital audio forensics aims to detect threats and fraud in audio signals.Contemporary audio forensic techniques use digital signal processing to detect the authenticity of recorded speech,recognize speakers,and recognize recording devices.User-generated audio recordings from mobile phones are very helpful in a number of forensic applications.This article proposed a novel method for recognizing recording devices based on recorded audio signals.First,a database of the features of various recording devices was constructed using 32 recording devices(20 mobile phones of different brands and 12 kinds of recording pens)in various environments.Second,the audio features of each recording device,such as the Mel-frequency cepstral coefficients(MFCC),were extracted from the audio signals and used as model inputs.Finally,support vector machines(SVM)with fractional Gaussian kernel were used to recognize the recording devices from their audio features.Experiments demonstrated that the proposed method had a 93.4%accuracy in recognizing recording devices.

关 键 词：Recording device recognition Mel-frequency cepstral coefficients support vector machines 

分 类 号：TN9[电子电信—信息与通信工程]