Speech source localization (SSL) using a microphone array aims to estimate the direction-of-arrival (DOA) of the speech source. However, its performance often degrades rapidly in reverberant environments. In this paper, a novel dual-microphone SSL algorithm is proposed to address this problem. First, the time-frequency regions dominated by direct sound are extracted by tracking the envelopes of speech, reverberation and background noise. The time-difference-of-arrival (TDOA) is then estimated by considering only these reliable regions. Second, a bin-wise de-aliasing strategy is introduced to make better use of the DOA information carried at high frequencies, where the spatial resolution is higher and there is typically less corruption by diffuse noise. Our experiments show that when compared with other widely-used algorithms, the proposed algorithm produces more reliable performance in realistic reverberant environments.
Cite as: Guo, Y., Wang, X., Wu, C., Fu, Q., Ma, N., Brown, G.J. (2016) A Robust Dual-Microphone Speech Source Localization Algorithm for Reverberant Environments. Proc. Interspeech 2016, 3354-3358, doi: 10.21437/Interspeech.2016-1063
@inproceedings{guo16c_interspeech,
author={Yanmeng Guo and Xiaofei Wang and Chao Wu and Qiang Fu and Ning Ma and Guy J. Brown},
title={{A Robust Dual-Microphone Speech Source Localization Algorithm for Reverberant Environments}},
year=2016,
booktitle={Proc. Interspeech 2016},
pages={3354--3358},
doi={10.21437/Interspeech.2016-1063}
}