Signal-informed DNN-based DOA Estimation combining an External Microphone and GCC-PHAT Features
Audio and Speech Processing
2022-06-14 v1 Sound
Abstract
Aiming at estimating the direction of arrival (DOA) of a desired speaker in a multi-talker environment using a microphone array, in this paper we propose a signal-informed method exploiting the availability of an external microphone attached to the desired speaker. The proposed method applies a binary mask to the GCC-PHAT input features of a convolutional neural network, where the binary mask is computed based on the power distribution of the external microphone signal. Experimental results for a reverberant scenario with up to four interfering speakers demonstrate that the signal-informed masking improves the localization accuracy, without requiring any knowledge about the interfering speakers.
Keywords
Cite
@article{arxiv.2206.05606,
title = {Signal-informed DNN-based DOA Estimation combining an External Microphone and GCC-PHAT Features},
author = {Ulrik Kowalk and Simon Doclo and Joerg Bitzer},
journal= {arXiv preprint arXiv:2206.05606},
year = {2022}
}