How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918343768801280 |
|---|---|
| author | Xiao, Yixuan Lux, Florian Pérez-González-de-Martos, Alejandro Vu, Ngoc Thang |
| author_facet | Xiao, Yixuan Lux, Florian Pérez-González-de-Martos, Alejandro Vu, Ngoc Thang |
| contents | Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically designed for speech synthesis, neural audio codecs were originally developed for compressing audio for storage and transmission. However, their ability to discretize speech also sparked interest in language-modeling-based speech synthesis. Owing to this dual functionality, codec resynthesized data may be labeled as either bonafide or spoof. So far, very little research has addressed this issue. In this study, we present a challenging extension of the ASVspoof 5 dataset constructed for this purpose. We examine how different labeling choices affect detection performance and provide insights into labeling strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16343 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection Xiao, Yixuan Lux, Florian Pérez-González-de-Martos, Alejandro Vu, Ngoc Thang Sound Machine Learning Since Text-to-Speech systems typically don't produce waveforms directly, recent spoof detection studies use resynthesized waveforms from vocoders and neural audio codecs to simulate an attacker. Unlike vocoders, which are specifically designed for speech synthesis, neural audio codecs were originally developed for compressing audio for storage and transmission. However, their ability to discretize speech also sparked interest in language-modeling-based speech synthesis. Owing to this dual functionality, codec resynthesized data may be labeled as either bonafide or spoof. So far, very little research has addressed this issue. In this study, we present a challenging extension of the ASVspoof 5 dataset constructed for this purpose. We examine how different labeling choices affect detection performance and provide insights into labeling strategies. |
| title | How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection |
| topic | Sound Machine Learning |
| url | https://arxiv.org/abs/2602.16343 |