Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture

TL;DR

This paper introduces a novel SE-Res2Net-Conformer architecture for detecting synthetic voices and audio splicing, improving spoofing detection performance and proposing a boundary detection approach for splicing.

Contribution

It extends Res2Net with Conformer blocks for better acoustic pattern exploitation and reformulates splicing detection as boundary detection using deep learning.

Findings

Improved spoofing detection on ASVspoof 2019 database.

Effective boundary detection for audio splicing.

Demonstrated superiority over existing methods.

Abstract

Synthetic voice and splicing audio clips have been generated to spoof Internet users and artificial intelligence (AI) technologies such as voice authentication. Existing research work treats spoofing countermeasures as a binary classification problem: bonafide vs. spoof. This paper extends the existing Res2Net by involving the recent Conformer block to further exploit the local patterns on acoustic features. Experimental results on ASVspoof 2019 database show that the proposed SE-Res2Net-Conformer architecture is able to improve the spoofing countermeasures performance for the logical access scenario. In addition, this paper also proposes to re-formulate the existing audio splicing detection problem. Instead of identifying the complete splicing segments, it is more useful to detect the boundaries of the spliced segments. Moreover, a deep learning approach can be used to solve the problem, which is different from the previous signal processing techniques.