Self-Supervised Pretraining for Robust Personalized Voice Activity Detection in Adverse Conditions

In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory (LSTM)-encoder using the autoregressive predictive coding (APC...

Full description

Saved in:
Bibliographic Details
Main Authors: Bovbjerg, Holger Severin, Jensen, Jesper, Ostergaard, Jan, Tan, Zheng-Hua
Format: Conference Proceeding
Language:English
Subjects:
Deep Learning
Noise reduction
Predictive coding
Robustness
Self-Supervised Learning
Signal processing
Supervised learning
Target Speaker
Training
Voice activity detection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we propose the use of self-supervised pretraining on a large unlabelled data set to improve the performance of a personalized voice activity detection (VAD) model in adverse conditions. We pretrain a long short-term memory (LSTM)-encoder using the autoregressive predictive coding (APC) framework and fine-tune it for personalized VAD. We also propose a denoising variant of APC, with the goal of improving the robustness of personalized VAD. The trained models are systematically evaluated on both clean speech and speech contaminated by various types of noise at different SNR-levels and compared to a purely supervised model. Our experiments show that self-supervised pretraining not only improves performance in clean conditions, but also yields models which are more robust to adverse conditions compared to purely supervised learning.
ISSN:2379-190X
DOI:10.1109/ICASSP48485.2024.10447653