Explainable Attribute-Based Speaker Verification
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_ | 1866910464323092480 |
|---|---|
| author | Wu, Xiaoliang Luu, Chau Bell, Peter Rajan, Ajitha |
| author_facet | Wu, Xiaoliang Luu, Chau Bell, Peter Rajan, Ajitha |
| contents | This paper proposes a fully explainable approach to speaker verification (SV), a task that fundamentally relies on individual speaker characteristics. The opaque use of speaker attributes in current SV systems raises concerns of trust. Addressing this, we propose an attribute-based explainable SV system that identifies speakers by comparing personal attributes such as gender, nationality, and age extracted automatically from voice recordings. We believe this approach better aligns with human reasoning, making it more understandable than traditional methods. Evaluated on the Voxceleb1 test set, the best performance of our system is comparable with the ground truth established when using all correct attributes, proving its efficacy. Whilst our approach sacrifices some performance compared to non-explainable methods, we believe that it moves us closer to the goal of transparent, interpretable AI and lays the groundwork for future enhancements through attribute expansion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19796 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explainable Attribute-Based Speaker Verification Wu, Xiaoliang Luu, Chau Bell, Peter Rajan, Ajitha Sound Artificial Intelligence Audio and Speech Processing This paper proposes a fully explainable approach to speaker verification (SV), a task that fundamentally relies on individual speaker characteristics. The opaque use of speaker attributes in current SV systems raises concerns of trust. Addressing this, we propose an attribute-based explainable SV system that identifies speakers by comparing personal attributes such as gender, nationality, and age extracted automatically from voice recordings. We believe this approach better aligns with human reasoning, making it more understandable than traditional methods. Evaluated on the Voxceleb1 test set, the best performance of our system is comparable with the ground truth established when using all correct attributes, proving its efficacy. Whilst our approach sacrifices some performance compared to non-explainable methods, we believe that it moves us closer to the goal of transparent, interpretable AI and lays the groundwork for future enhancements through attribute expansion. |
| title | Explainable Attribute-Based Speaker Verification |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.19796 |