Saved in:
Bibliographic Details
Main Authors: Feng, Fuyuan, Zhang, Wenbin, Gao, Yu, Xu, Longting, Mou, Xiaofeng, Xu, Yi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.12769
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911384270274560
author Feng, Fuyuan
Zhang, Wenbin
Gao, Yu
Xu, Longting
Mou, Xiaofeng
Xu, Yi
author_facet Feng, Fuyuan
Zhang, Wenbin
Gao, Yu
Xu, Longting
Mou, Xiaofeng
Xu, Yi
contents Personal Voice Activity Detection (PVAD) is crucial for identifying target speaker segments in the mixture, yet its performance heavily depends on the quality of speaker embeddings. A key practical limitation is the short enrollment speech--such as a wake-up word--which provides limited cues. This paper proposes a novel adaptive speaker embedding self-augmentation strategy that enhances PVAD performance by augmenting the original enrollment embeddings through additive fusion of keyframe embeddings extracted from mixed speech. Furthermore, we introduce a long-term adaptation strategy to iteratively refine embeddings during detection, mitigating speaker temporal variability. Experiments show significant gains in recall, precision, and F1-score under short enrollment conditions, matching full-length enrollment performance after five iterative updates. The source code is available at https://anonymous.4open.science/r/ASE-PVAD-E5D6 .
format Preprint
id arxiv_https___arxiv_org_abs_2601_12769
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Adaptive Speaker Embedding Self-Augmentation for Personal Voice Activity Detection with Short Enrollment Speech
Feng, Fuyuan
Zhang, Wenbin
Gao, Yu
Xu, Longting
Mou, Xiaofeng
Xu, Yi
Audio and Speech Processing
Personal Voice Activity Detection (PVAD) is crucial for identifying target speaker segments in the mixture, yet its performance heavily depends on the quality of speaker embeddings. A key practical limitation is the short enrollment speech--such as a wake-up word--which provides limited cues. This paper proposes a novel adaptive speaker embedding self-augmentation strategy that enhances PVAD performance by augmenting the original enrollment embeddings through additive fusion of keyframe embeddings extracted from mixed speech. Furthermore, we introduce a long-term adaptation strategy to iteratively refine embeddings during detection, mitigating speaker temporal variability. Experiments show significant gains in recall, precision, and F1-score under short enrollment conditions, matching full-length enrollment performance after five iterative updates. The source code is available at https://anonymous.4open.science/r/ASE-PVAD-E5D6 .
title Adaptive Speaker Embedding Self-Augmentation for Personal Voice Activity Detection with Short Enrollment Speech
topic Audio and Speech Processing
url https://arxiv.org/abs/2601.12769