Unsupervised adversarial domain adaptation for acoustic scene classification
This addresses the issue of domain shift in acoustic scene classification for researchers and practitioners, but it is incremental as it applies an existing adversarial adaptation approach to a new domain.
The paper tackles the problem of mismatched conditions between training and testing data in acoustic scene classification, which reduces accuracy, by proposing an unsupervised adversarial domain adaptation method that achieves about a 10% increase in accuracy on an unseen, unlabeled dataset while maintaining similar performance on the labeled dataset.
A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy. As a countermeasure, we present the first method of unsupervised adversarial domain adaptation for acoustic scene classification. We employ a model pre-trained on data from one set of conditions and by using data from other set of conditions, we adapt the model in order that its output cannot be used for classifying the set of conditions that input data belong to. We use a freely available dataset from the DCASE 2018 challenge Task 1, subtask B, that contains data from mismatched recording devices. We consider the scenario where the annotations are available for the data recorded from one device, but not for the rest. Our results show that with our model agnostic method we can achieve $\sim 10\%$ increase at the accuracy on an unseen and unlabeled dataset, while keeping almost the same performance on the labeled dataset.