Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection

TL;DR

This paper introduces a novel multi-perspective information fusion Res2Net model combined with random Specmix data augmentation to enhance fake speech detection, especially in low-quality scenarios, by improving model focus and generalization.

Contribution

The paper proposes a new MPIF-Res2Net architecture with random Specmix augmentation to better locate discriminative features and reduce redundant information in fake speech detection.

Findings

Achieved 3.29% EER on ASVspoof 2021 LA dataset.

Improved model generalization through random Specmix augmentation.

Effectively reduced redundant interference information in fake speech detection.

Abstract

In this paper, we propose the multi-perspective information fusion (MPIF) Res2Net with random Specmix for fake speech detection (FSD). The main purpose of this system is to improve the model's ability to learn precise forgery information for FSD task in low-quality scenarios. The task of random Specmix, a data augmentation, is to improve the generalization ability of the model and enhance the model's ability to locate discriminative information. Specmix cuts and pastes the frequency dimension information of the spectrogram in the same batch of samples without introducing other data, which helps the model to locate the really useful information. At the same time, we randomly select samples for augmentation to reduce the impact of data augmentation directly changing all the data. Once the purpose of helping the model to locate information is achieved, it is also important to reduce unnecessary information. The role of MPIF-Res2Net is to reduce redundant interference information. Deceptive information from a single perspective is always similar, so the model learning this similar information will produce redundant spoofing clues and interfere with truly discriminative information. The proposed MPIF-Res2Net fuses information from different perspectives, making the information learned by the model more diverse, thereby reducing the redundancy caused by similar information and avoiding interference with the learning of discriminative information. The results on the ASVspoof 2021 LA dataset demonstrate the effectiveness of our proposed method, achieving EER and min-tDCF of 3.29% and 0.2557, respectively.