Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization
This work tackles the problem of costly data labeling for sound source localization, making deep learning approaches more practical for researchers and engineers working with real-world acoustic data.
This paper addresses the challenge of localizing multiple sound sources using deep neural networks, which typically require extensive labeled data. The authors propose an ensemble of discriminators to enhance domain adaptation, allowing models trained on synthetic data to perform better with real-world recordings without requiring real-world labels.
This paper introduces an ensemble of discriminators that improves the accuracy of a domain adaptation technique for the localization of multiple sound sources. Recently, deep neural networks have led to promising results for this task, yet they require a large amount of labeled data for training. Recording and labeling such datasets is very costly, especially because data needs to be diverse enough to cover different acoustic conditions. In this paper, we leverage acoustic simulators to inexpensively generate labeled training samples. However, models trained on synthetic data tend to perform poorly with real-world recordings due to the domain mismatch. For this, we explore two domain adaptation methods using adversarial learning for sound source localization which use labeled synthetic data and unlabeled real data. We propose a novel ensemble approach that combines discriminators applied at different feature levels of the localization model. Experiments show that our ensemble discrimination method significantly improves the localization performance without requiring any label from the real data.