Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910618588545024 |
|---|---|
| author | Gupta, Shubham Ravanelli, Mirco Germain, Pascal Subakan, Cem |
| author_facet | Gupta, Shubham Ravanelli, Mirco Germain, Pascal Subakan, Cem |
| contents | In this paper, we propose Phoneme Discretized Saliency Maps (PDSM), a discretization algorithm for saliency maps that takes advantage of phoneme boundaries for explainable detection of AI-generated voice. We experimentally show with two different Text-to-Speech systems (i.e., Tacotron2 and Fastspeech2) that the proposed algorithm produces saliency maps that result in more faithful explanations compared to standard posthoc explanation methods. Moreover, by associating the saliency maps to the phoneme representations, this methodology generates explanations that tend to be more understandable than standard saliency maps on magnitude spectrograms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10422 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice Gupta, Shubham Ravanelli, Mirco Germain, Pascal Subakan, Cem Audio and Speech Processing Sound Signal Processing In this paper, we propose Phoneme Discretized Saliency Maps (PDSM), a discretization algorithm for saliency maps that takes advantage of phoneme boundaries for explainable detection of AI-generated voice. We experimentally show with two different Text-to-Speech systems (i.e., Tacotron2 and Fastspeech2) that the proposed algorithm produces saliency maps that result in more faithful explanations compared to standard posthoc explanation methods. Moreover, by associating the saliency maps to the phoneme representations, this methodology generates explanations that tend to be more understandable than standard saliency maps on magnitude spectrograms. |
| title | Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice |
| topic | Audio and Speech Processing Sound Signal Processing |
| url | https://arxiv.org/abs/2406.10422 |