Conference paper
Exploiting Non-Negative Matrix Factorization for Binaural Sound Localization in the Presence of Directional Interference
Hearing Systems Group, Hearing Systems Section, Department of Health Technology, Technical University of Denmark1
Hearing Systems Section, Department of Health Technology, Technical University of Denmark2
Department of Health Technology, Technical University of Denmark3
University of Sheffield4
This study presents a novel solution to the problem of binaural localization of a speaker in the presence of interfering directional noise and reverberation. Using a state-of-the-art binaural localization algorithm based on a deep neural network (DNN), we propose adding a source separation stage based on non-negative matrix factorization (NMF) to improve the localization performance in conditions with interfering sources.
The separation stage is coupled with the localization stage and is optimized with respect to a broad range of different acoustic conditions, emphasizing a robust and generalizable solution. The machine listening system is shown to greatly benefit from the NMF-based separation stage at low target-to-masker ratios (TMRs) for a variety of noise types, especially for non-stationary noise.
It is also demonstrated that training the NMF algorithm on anechoic speech provides better performance than using reverberant speech, and that optimizing the source separation stage using a localization metric rather than a source separation metric substantially increases the system performance.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2021 |
Pages: | 221-225 |
Proceedings: | 2021 IEEE International Conference on Acoustics, Speech and Signal Processing |
ISBN: | 1728176050 , 1728176069 , 9781728176055 and 9781728176062 |
ISSN: | 2379190x and 15206149 |
Types: | Conference paper |
DOI: | 10.1109/ICASSP39728.2021.9414233 |
ORCIDs: | Ornolfsson, Ingvi , Dau, Torsten and May, Tobias |