Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.14959 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912912483811328 |
|---|---|
| author | Selitskiy, Anton Shahriyar, Akib Prakasan, Jishnuraj |
| author_facet | Selitskiy, Anton Shahriyar, Akib Prakasan, Jishnuraj |
| contents | In this paper, we introduce the discrete optimal transport voice conversion ($k$DOT-VC) method. Comparison with $k$NN-VC, SinkVC, and Gaussian optimal transport (MKL) demonstrates stronger domain adaptation abilities of our method. We use the probabilistic nature of optimal transport (OT) and show that $k$DOT-VC is an effective black-box adversarial attack against modern audio anti-spoofing countermeasures (CMs). Our attack operates as a post-processing, distribution-alignment step: frame-level {WavLM} embeddings of generated speech are aligned to an unpaired bona fide pool via entropic OT and a top-$k$ barycentric projection, then decoded with a neural vocoder. Ablation analysis indicates that distribution-level alignment is a powerful and stable attack for deployed CMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Discrete optimal transport is a strong audio adversarial attack Selitskiy, Anton Shahriyar, Akib Prakasan, Jishnuraj Audio and Speech Processing Artificial Intelligence In this paper, we introduce the discrete optimal transport voice conversion ($k$DOT-VC) method. Comparison with $k$NN-VC, SinkVC, and Gaussian optimal transport (MKL) demonstrates stronger domain adaptation abilities of our method. We use the probabilistic nature of optimal transport (OT) and show that $k$DOT-VC is an effective black-box adversarial attack against modern audio anti-spoofing countermeasures (CMs). Our attack operates as a post-processing, distribution-alignment step: frame-level {WavLM} embeddings of generated speech are aligned to an unpaired bona fide pool via entropic OT and a top-$k$ barycentric projection, then decoded with a neural vocoder. Ablation analysis indicates that distribution-level alignment is a powerful and stable attack for deployed CMs. |
| title | Discrete optimal transport is a strong audio adversarial attack |
| topic | Audio and Speech Processing Artificial Intelligence |
| url | https://arxiv.org/abs/2509.14959 |