MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction

Abstract

Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice. We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion. In training data selection, we demonstrate that MOS enables effective filtering of samples from unbalanced datasets. In the model fusion, our results demonstrate that incorporating MOS as a gating mechanism in FAD model fusion enhances overall performance.

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keyzhou2024mos

Related papers

• Neural MOS Prediction For Synthesized Speech Using Multi-task Learning With Spoofing Detection And Spoofing Type Classification (2020)9.59
• SAMOS: A Neural MOS Prediction Model Leveraging Semantic Representations And Acoustic Features (2024)2.26
• RAMP: Retrieval-augmented MOS Prediction Via Confidence-based Dynamic Weighting (2023)9.03
• Ldnet: Unified Listener Dependent Modeling In MOS Prediction For Synthetic Speech (2021)12.74
• DDOS: A MOS Prediction Framework Utilizing Domain Adaptive Pre-training And Distribution Of Opinion Scores (2022)9.03
• LE-SSL-MOS: Self-supervised Learning MOS Prediction With Listener Enhancement (2023)9.23
• Automos: Learning A Non-intrusive Assessor Of Naturalness-of-speech (2016)0.00
• Investigating Content-aware Neural Text-to-speech MOS Prediction Using Prosodic And Linguistic Features (2022)6.34