Profile-Error-Tolerant Target-Speaker Voice Activity Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Dongmei, Xiao, Xiong, Kanda, Naoyuki, Yousefi, Midia, Yoshioka, Takuya, Wu, Jian
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909160176615424
author Wang, Dongmei
Xiao, Xiong
Kanda, Naoyuki
Yousefi, Midia
Yoshioka, Takuya
Wu, Jian
author_facet Wang, Dongmei
Xiao, Xiong
Kanda, Naoyuki
Yousefi, Midia
Yoshioka, Takuya
Wu, Jian
contents Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer from errors in speaker profiles, as those profiles are typically obtained by running a traditional clustering-based diarization method over the input signal. This paper proposes an extension to TS-VAD, called Profile-Error-Tolerant TS-VAD (PET-TSVAD), which is robust to such speaker profile errors. This is achieved by employing transformer-based TS-VAD that can handle a variable number of speakers and further introducing a set of additional pseudo-speaker profiles to handle speakers undetected during the first pass diarization. During training, we use speaker profiles estimated by multiple different clustering algorithms to reduce the mismatch between the training and testing conditions regarding speaker profiles. Experimental results show that PET-TSVAD consistently outperforms the existing TS-VAD method on both the VoxConverse and DIHARD-I datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2309_12521
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Profile-Error-Tolerant Target-Speaker Voice Activity Detection
Wang, Dongmei
Xiao, Xiong
Kanda, Naoyuki
Yousefi, Midia
Yoshioka, Takuya
Wu, Jian
Sound
Audio and Speech Processing
Target-Speaker Voice Activity Detection (TS-VAD) utilizes a set of speaker profiles alongside an input audio signal to perform speaker diarization. While its superiority over conventional methods has been demonstrated, the method can suffer from errors in speaker profiles, as those profiles are typically obtained by running a traditional clustering-based diarization method over the input signal. This paper proposes an extension to TS-VAD, called Profile-Error-Tolerant TS-VAD (PET-TSVAD), which is robust to such speaker profile errors. This is achieved by employing transformer-based TS-VAD that can handle a variable number of speakers and further introducing a set of additional pseudo-speaker profiles to handle speakers undetected during the first pass diarization. During training, we use speaker profiles estimated by multiple different clustering algorithms to reduce the mismatch between the training and testing conditions regarding speaker profiles. Experimental results show that PET-TSVAD consistently outperforms the existing TS-VAD method on both the VoxConverse and DIHARD-I datasets.
title Profile-Error-Tolerant Target-Speaker Voice Activity Detection
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2309.12521