Multi-Level Information Aggregation Based Graph Attention Networks Towards Fake Speech Detection
- 3 June 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 31 (10709908) , 1580-1584
Abstract
It is widely acknowledged that distinguishing genuine speech from spoofed speech encompasses various subbands and temporal segments within speech signals. However, prevailing spoofing detection methods tend to oversimplify the relationships between these cues by employing linear models. In this paper, we introduce a multi-level information aggregation Graph Attention Networks (MiaGATs) to generate highly discriminative features for fake speech detection (FSD). In MiaGATs, each subband and temporal segment of a speech signal is represented as distinct nodes. MiaGATs incorporates channel information aggregation within each node to effectively harness the unique spectral and temporal characteristics during the feature encoding stage. In particular, MiaGATs address the interactions between nodes through indirect node aggregation and integrates both indirect and direct node aggregation by max-pooling operation. Experimental results on ASVspoof2019 and ASVspoof2021 LA databases show significant relative improvement compared to the current state-of-the-art. In comparison to the leading integrated spectro-temporal graph attention networks, MiaGATs gains an impressive performance improvement in various conditions, underscoring MiaGATs's position as a new benchmark in spoofing detection performance.Keywords
Funding Information
- National Natural Science Foundation of China Joint Fund Key Project (U2003207)
- National Natural Science Foundation of China (62201002)
- Natural Science Foundation of Anhui Province (1908085MF209)
This publication has 31 references indexed in Scilit:
- A Fused Speech Enhancement Framework for Robust Speaker VerificationIEEE Signal Processing Letters, 2023
- SAMO: Speaker Attractor Multi-Center One-Class Learning For Voice Anti-Spoofing2023
- The Clever Hans Effect in Voice Spoofing Detection2023
- AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks2022
- Dynamic Convolution With Global-Local Information for Session-Invariant Speaker Representation LearningIEEE Signal Processing Letters, 2021
- Improved Lightcnn with Attention Modules for Asv Spoofing Detection2021
- Towards End-to-End Synthetic Speech DetectionIEEE Signal Processing Letters, 2021
- A Capsule Network Based Approach for Detection of Audio Spoofing Attacks2021
- Spoofing and countermeasures for speaker verification: A surveySpeech Communication, 2015
- Speaker Verification Using Adapted Gaussian Mixture ModelsDigital Signal Processing, 2000