N Ma, T May, H Wierstorf, G J Brown, "A machine-hearing system exploiting head movements for binaural sound localisation in reverberant conditions," in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), p. 2699-2703 (2015). [ link ]
Bibtex
@inproceedings{Ma2015,
title = {A machine-hearing system exploiting head movements for
binaural sound localisation in reverberant conditions},
author = {Ma, Ning and May, Tobias and Wierstorf, Hagen
and Brown, Guy J.},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal
Processing (ICASSP)},
address = {Brisbane, Australia},
pages = {2699--2703},
month = {April},
year = {2015},
doi = {10.1109/ICASSP.2015.7178461},
url = {https://doi.org/10.1109/ICASSP.2015.7178461}
}
Abstract
This paper is concerned with machine localisation of multiple active speech sources in reverberant environments using two (binaural) microphones. Such conditions typically present a problem for `classical’ binaural models. Inspired by the human ability to utilise head movements, the current study investigated the influence of different head movement strategies on binaural sound localisation. A machine-hearing system that exploits a multi-step head rotation strategy for sound localisation was found to produce the best performance in simulated reverberant acoustic space. This paper also reports the public release of a free binaural room impulse responses (BRIRs) database that allows the simulation of head rotation used in this study.