Polynomial eigenvalue decomposition-based target speaker voice activity detection in the presence of competing talkers
File(s)
Author(s)
Neo, Vincent Weisheng
Weiss, Stephan
McKnight, Simon
Hogg, Aidan
Naylor, Patrick A
Type
Conference Paper
Abstract
Voice activity detection (VAD) algorithms are essential for many speech processing applications, such as speaker diarization, automatic speech recognition, speech enhancement, and speech coding. With a good VAD algorithm, non-speech segments can be excluded to improve the performance and computation of these applications. In this paper, we propose a polynomial eigenvalue decomposition-based target-speaker VAD algorithm to detect unseen target speakers in the presence of competing talkers. The proposed approach uses frame-based processing to compute the syndrome energy, used for testing the presence or absence of a target speaker. The proposed approach is consistently among the best in F1 and balanced accuracy scores over the investigated range of signal to interference ratio (SIR) from -10 dB to 20 dB.
Date Issued
2022-10-17
Date Acceptance
2022-07-01
Citation
2022, pp.1-5
Publisher
IEEE
Start Page
1
End Page
5
Copyright Statement
Copyright © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
https://ieeexplore.ieee.org/document/9914796
Source
International Workshop on Acoustic Signal Enhancement (IWAENC)
Publication Status
Published
Start Date
2022-09-05
Coverage Spatial
Bamberg, Germany
Date Publish Online
2022-09-08