arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1602.05682cs.SDcs.LG
收藏

基于深度学习的录音设备识别

Audio Recording Device Identification Based on Deep Learning

Shanghai Jiao Tong University(上海交通大学)

Simeng Qi, Zheng Huang, Yan Li, Shaopei Shi

摘要:

本文提出了一种从背景噪声中识别录音设备的方法,从而为取证提供了一种方法。音频信号是语音信号和噪声信号之和。语音信号承载着信息的传递,因此受到人们的广泛关注。因此,为了获得更高的信噪比,人们进行了大量的研究。有很多语音增强算法都是为了提高语音的质量,可以看作是降低噪声。然而,噪声可以被视为音频记录设备的固有指纹痕迹。这些数字痕迹可以通过新的机器学习技术来表征和识别。因此,在我们的研究中,我们使用噪声作为本征特征。对于识别,使用并比较了深度学习方法的多个分类器。识别结果表明,从各设备噪声中提取特征向量,并利用深度学习技术进行识别的方法是可行的,且效果良好。

英文摘要:

In this paper we present a research on identification of audio recording devices from background noise, thus providing a method for forensics. The audio signal is the sum of speech signal and noise signal. Usually, people pay more attention to speech signal, because it carries the information to deliver. So a great amount of researches have been dedicated to getting higher Signal-Noise-Ratio (SNR). There are many speech enhancement algorithms to improve the quality of the speech, which can be seen as reducing the noise. However, noises can be regarded as the intrinsic fingerprint traces of an audio recording device. These digital traces can be characterized and identified by new machine learning techniques. Therefore, in our research, we use the noise as the intrinsic features. As for the identification, multiple classifiers of deep learning methods are used and compared. The identification result shows that the method of getting feature vector from the noise of each device and identifying them with deep learning techniques is viable, and well-preformed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑