Distribution mismatches between the data seen at training and at application time remain a major challenge in all application areas of machine learning. We study this problem in the context of machine listening (Task 1b of the DCASE 2019 Challenge). We propose a novel approach to learn domain-invariant classifiers in an end-to-end fashion by enforcing equal hidden layer representations for domain-parallel samples, i.e. time-aligned recordings from different recording devices. No classification labels are needed for our domain adaptation (DA) method, which makes the data collection process cheaper.
@article{arxiv.1909.02869,
title = {Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification},
author = {Paul Primus and Hamid Eghbal-zadeh and David Eitelsebner and Khaled Koutini and Andreas Arzt and Gerhard Widmer},
journal= {arXiv preprint arXiv:1909.02869},
year = {2019}
}
Comments
Published at the Workshop on Detection and Classification of Acoustic Scenes and Events, 25-26 October 2019, New York, USA