ASLNet: An Encoder-Decoder Architecture for Audio Splicing Detection and Localization

Abstract

Audio splicing means inserting an audio segment into another audio, which presents a great challenge to audio forensics. In this paper, a novel audio splicing detection and localization method based on an encoder-decoder architecture (ASLNet) is proposed. Firstly, an audio clip is divided into several small audio segments according to the size of the smallest localization region $\left(L_{\text{slr}}\right)$ , and the acoustic feature matrix and corresponding binary ground truth mask are created from each audio segment. Then, we concatenate acoustic feature matrices from all segments of an audio clip into an acoustic feature matrix and send it to a fully convolutional network (FCN) based encoder-decoder architecture which consists of a series of convolutional, pooling and transposed convolutional layers to get a binary output mask. Next, the binary output mask is divided into small segments according to the $L_{\text{slr}}$ , and the ratio $\left(\rho \right)$ of the number of elements equal to one to the number of all elements in a small segment is calculated. Finally, we compare $\rho$ with the predetermined threshold $T$ to determine whether the corresponding audio segment is spliced. We evaluate the effectiveness of the proposed ASLNet on four datasets produced from publicly available speech corpus. Extensive experiments show that the best detection accuracy of ASLNet for the intradatabase and cross-database evaluation can achieve 0.9965 and 0.9740 receptively, which outperforms the state-of-the-art method.