English

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}
}
R2 v1 2026-06-24T11:47:41.863Z