Audio Recording Device Identification Based on Deep Learning

TL;DR

This paper explores identifying audio recording devices by analyzing background noise using deep learning, demonstrating that noise features serve as reliable device fingerprints for forensic purposes.

Contribution

It introduces a novel approach of using noise as intrinsic features for device identification and compares multiple deep learning classifiers for improved accuracy.

Findings

Deep learning classifiers effectively identify devices from noise features.

Noise-based identification is viable despite focus on speech enhancement.

Method outperforms traditional techniques in device fingerprinting.

Abstract

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.