Saved in:
Bibliographic Details
Main Authors: Nejad, Mahsa Ghazvini, Asl, Hamed Jafarzadeh, Edraki, Amin, Sadeghi, Mohammadreza, Asgharian, Masoud, Yu, Yuanhao, Nia, Vahid Partovi
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