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

View on arXiv ← Back to list

Authors: Shunbo Dong, Jun Xue, Cunhang Fan, Kang Zhu, Yujie Chen, Zhao Lv

Published: 2023-06-27 11:27:55+00:00

AI Summary

This paper proposes MPIF-Res2Net with random Specmix for fake speech detection, aiming to improve the model's ability to learn precise forgery information in low-quality scenarios. The approach uses multi-perspective information fusion to reduce redundant information and random Specmix for data augmentation to enhance generalization and improve discriminative information location.

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.

Key findings

The proposed method achieved an EER of 3.29% and a min-tDCF of 0.2557 on the ASVspoof 2021 LA dataset. The random Specmix strategy and the MPIF module were shown to be effective in improving the model's performance, particularly in low-quality scenarios. The single-system approach is less complex than other fusion-based systems achieving comparable results.

Approach

The proposed method utilizes a multi-perspective information fusion (MPIF) module within a Res2Net architecture to reduce redundant information from single-perspective analysis of spoofing clues. It also incorporates a random Specmix data augmentation strategy to improve the model's generalization ability and focus on discriminative features.

Datasets

ASVspoof 2021 LA dataset

Model(s)

MPIF-Res2Net

Author countries

China

← Previous