Beamformer-Guided Target Speaker Extraction
Abstract
We propose a Beamformer-guided Target Speaker Extraction (BG-TSE) method to extract a target speaker's voice from a multi-channel recording informed by the direction of arrival of the target. The proposed method employs a front-end beamformer steered towards the target speaker to provide an auxiliary signal to a single-channel TSE system. By allowing for time-varying embeddings in the single-channel TSE block, the proposed method fully exploits the correspondence between the front-end beamformer output and the target speech in the microphone signal. Experimental evaluation on simulated multi-channel 2-speaker mixtures, in both anechoic and reverberant conditions, demonstrates the advantage of the proposed method compared to recent single-channel and multi-channel baselines.
Keywords
Cite
@article{arxiv.2303.08702,
title = {Beamformer-Guided Target Speaker Extraction},
author = {Mohamed Elminshawi and Srikanth Raj Chetupalli and Emanuël A. P. Habets},
journal= {arXiv preprint arXiv:2303.08702},
year = {2023}
}
Comments
Submitted to the 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023)