Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.12947 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914383581413376 |
|---|---|
| author | Nejad, Mahsa Ghazvini Asl, Hamed Jafarzadeh Edraki, Amin Sadeghi, Mohammadreza Asgharian, Masoud Yu, Yuanhao Nia, Vahid Partovi |
| author_facet | Nejad, Mahsa Ghazvini Asl, Hamed Jafarzadeh Edraki, Amin Sadeghi, Mohammadreza Asgharian, Masoud Yu, Yuanhao Nia, Vahid Partovi |
| contents | Personalized Voice Activity Detection (PVAD) systems activate only in response to a specific target speaker. Speaker-conditioning methods are employed to inject information about the target speaker into a VAD pipeline, to achieve personalization. Existing speaker-conditioning methods typically modify the inputs or activations of a VAD model. We propose an alternative perspective to speaker conditioning. Our approach, HyWA, employs a hypernetwork to generate personalized weights for a few selected layers of a standard VAD model. We evaluate HyWA against multiple baseline speaker-conditioning techniques using a fixed backbone VAD. Our comparison shows consistent improvements in PVAD performance. This new approach improves the current speaker-conditioning techniques in two ways: i) increases the mean average precision, ii) facilitates deployment by reusing the same VAD architecture. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HyWA: Hypernetwork Weight Adapting Personalized Voice Activity Detection Nejad, Mahsa Ghazvini Asl, Hamed Jafarzadeh Edraki, Amin Sadeghi, Mohammadreza Asgharian, Masoud Yu, Yuanhao Nia, Vahid Partovi Audio and Speech Processing Artificial Intelligence Machine Learning Sound Personalized Voice Activity Detection (PVAD) systems activate only in response to a specific target speaker. Speaker-conditioning methods are employed to inject information about the target speaker into a VAD pipeline, to achieve personalization. Existing speaker-conditioning methods typically modify the inputs or activations of a VAD model. We propose an alternative perspective to speaker conditioning. Our approach, HyWA, employs a hypernetwork to generate personalized weights for a few selected layers of a standard VAD model. We evaluate HyWA against multiple baseline speaker-conditioning techniques using a fixed backbone VAD. Our comparison shows consistent improvements in PVAD performance. This new approach improves the current speaker-conditioning techniques in two ways: i) increases the mean average precision, ii) facilitates deployment by reusing the same VAD architecture. |
| title | HyWA: Hypernetwork Weight Adapting Personalized Voice Activity Detection |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound |
| url | https://arxiv.org/abs/2510.12947 |