Name
Abstract | ||
|---|---|---|
Sound source localization is a cumbersome task in challenging reverberation conditions. Recently, there is a growing interest in developing learning-based localization methods. In this approach, acoustic features are extracted from the measured signals and then given as input to a model that maps them to the corresponding source positions. Typically, a massive dataset of labeled samples from known positions is required to train such models. Here, we present a novel weakly-supervised deep-learning localization method that exploits only a few labeled (anchor) samples with known positions, together with a larger set of unlabeled samples, for which we only know their relative physical ordering. We design an architecture that uses a stochastic combination of triplet-ranking loss for the unlabeled samples and physical loss for the anchor samples, to learn a nonlinear deep embedding that maps acoustic features to an azimuth angle of the source. The combined loss can be optimized effectively using standard gradient-based approach. Evaluating the proposed approach on simulated data, we demonstrate its significant improvement over two previous learning-based approaches for various reverberation levels, while maintaining consistent performance with varying sizes of labeled data. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/WASPAA.2019.8937159 | 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) |
Keywords | Field | DocType |
acoustic source localization,deep embedding learning,triplet-loss,relative transfer function | Embedding,Nonlinear system,Reverberation,Pattern recognition,Ranking,Computer science,Azimuth,Artificial intelligence,Labeled data,Acoustics,Acoustic source localization,Triplet loss | Conference |
ISSN | ISBN | Citations |
1931-1168 | 978-1-7281-1124-7 | 0 |
PageRank | References | Authors |
0.34 | 14 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Renana Opochinsky | 1 | 0 | 0.34 |
| Bracha Laufer-Goldshtein | 2 | 21 | 5.22 |
| Sharon Gannot | 3 | 1754 | 130.51 |
| Gal Chechik | 4 | 823 | 74.06 |