Unsupervised adversarial domain adaptation for acoustic scene classification
By Shayan Gharib, Konstantinos Drossos, Emre Çakir, Dmitriy Serdyuk, Tuomas Virtanen. 2018
46 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Eduardo Fonseca
- Xavier Favory
- Xavier Serra
- Frederic Font
- Jordi Pons
- Konstantinos Drossos
- Andrés F. Pérez
- Shayan Gharib
Citations in the corpus
- FSD50K: An Open Dataset of Human-Labeled Sound Events (2020, background): “AudioSet, we hope that a number of tasks become possible, such as experimenting with domain adaptation techniques [96], or cross-dataset evaluation [97] under different acoustic conditions.”
- Audio-Visual Model Distillation Using Acoustic Images (2019, methodology): “Current methods, even best deep learning models, lead to very low classification accuracies [14, 29] in such conditions.”
- VOICe: A Sound Event Detection Dataset For Generalizable Domain Adaptation (2019, methodology): “The adaptation method of our work was initially introduced in [20].”