In this contribution, we address the problem of speech separation from concurrent speakers through the use of a binaural processor. In this system, we take advantage of both ITDs (Inter-aural Time Differences) and ILDs (Inter-aural Level Difs.) present in the binaural input signals to perform spatial localisation and discrimination. However, in applications as Forensic Acoustics where hidden recordings are desired we cannot make use of head simulators, but we can also obtain ITDs and ILDs through stereo recordings with a cardioid microphone pair. In this way, after a new training of the processor, we are able to extract the information arriving from the desired direction from a simple stereo recording. Several experiments with static and moving speakers have been performed, and some audio results on concurrent speakers separation are also included.
Cite as: Gonzalez-Rodriguez, J., Cruz-Llanas, S., Ortega-Garcia, J. (1999) Concurrent speakers separation through binaural processing of stereo recordings. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 2595-2598, doi: 10.21437/Eurospeech.1999-571
@inproceedings{gonzalezrodriguez99_eurospeech,
author={Joaquin Gonzalez-Rodriguez and Santiago Cruz-Llanas and Javier Ortega-Garcia},
title={{Concurrent speakers separation through binaural processing of stereo recordings}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={2595--2598},
doi={10.21437/Eurospeech.1999-571}
}