GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios
Guanjun Li, Wei Xue, Wenju Liu, Jiangyan Yi, Jianhua Tao
Abstract
Existing noise-robust and reverberant-robust localization algorithms fail to localize the target speaker when interfering speakers are present. In this paper, we address the problem of localizing only the target speaker in multi-speaker scenarios and propose a target speaker localization algorithm, called GCC-speaker. Specifically, we modify the weighting of the generalized cross-correlation with phase transform (GCC-PHAT) algorithm and propose an optimal speaker-dependent weighting based on a novel localization-related loss function and data-driven training. The speaker-dependent weighting is responsible for guiding the GCC algorithm to obtain the optimal target speaker localization results. As for the loss function, we constrain the estimated GCC angular spectrum and the estimated direction of arrival (DOA) to be close to their ground truth values, respectively. The experimental results show the superiority of GCC-speaker compared to the existing target speaker localization algorithms for different signal-to-interference ratios, reverberation times and array geometries.
BibTeX
@inproceedings{icassp2023_gccspeakertarget,
title = {GCC-Speaker: Target Speaker Localization with Optimal Speaker-Dependent Weighting in Multi-Speaker Scenarios},
author = {Guanjun Li and Wei Xue and Wenju Liu and Jiangyan Yi and Jianhua Tao},
booktitle = {ICASSP 2023},
year = {2023}
}