Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings
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_ | 1866913088421232640 |
|---|---|
| author | Nallaguntla, Vamshi Kshirsagar, Shruti Avila, Anderson R. |
| author_facet | Nallaguntla, Vamshi Kshirsagar, Shruti Avila, Anderson R. |
| contents | Recent advances in emotional voice conversion (EVC) have enabled the generation of expressive synthetic speech, raising new concerns in audio deepfake detection. Existing approaches treat speech as a homogeneous signal and largely overlook its internal phonetic structure, limiting their interpretability in emotionally conditioned settings. In this work, we propose a phoneme-level framework to analyze emotionally manipulated synthetic speech using real and EVC-generated speech under matched emotional conditions with shared transcripts, phoneme-aligned TextGrids, and WavLM-based embeddings. Our results show that phoneme behavior varies across categories, with complex vowels and fricatives exhibiting higher divergence while simpler phonemes remain more stable. Phonemes with larger distributional differences are also found to be more easily detected, consistently across multiple emotions and synthesis systems. These findings demonstrate that phoneme-level analysis is an effective and interpretable approach for detecting emotionally manipulated synthetic speech. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03079 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings Nallaguntla, Vamshi Kshirsagar, Shruti Avila, Anderson R. Sound Machine Learning Audio and Speech Processing Recent advances in emotional voice conversion (EVC) have enabled the generation of expressive synthetic speech, raising new concerns in audio deepfake detection. Existing approaches treat speech as a homogeneous signal and largely overlook its internal phonetic structure, limiting their interpretability in emotionally conditioned settings. In this work, we propose a phoneme-level framework to analyze emotionally manipulated synthetic speech using real and EVC-generated speech under matched emotional conditions with shared transcripts, phoneme-aligned TextGrids, and WavLM-based embeddings. Our results show that phoneme behavior varies across categories, with complex vowels and fricatives exhibiting higher divergence while simpler phonemes remain more stable. Phonemes with larger distributional differences are also found to be more easily detected, consistently across multiple emotions and synthesis systems. These findings demonstrate that phoneme-level analysis is an effective and interpretable approach for detecting emotionally manipulated synthetic speech. |
| title | Phoneme-Level Deepfake Detection Across Emotional Conditions Using Self-Supervised Embeddings |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2605.03079 |