Unsupervised adversarial domain adaptation for acoustic scene classification

Abstract

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.

Cited by in corpus (10)

• ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users
• Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices
• Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification
• VOICe: A Sound Event Detection Dataset For Generalizable Domain Adaptation
• CNN-based Discriminative Training for Domain Compensation in Acoustic Event Detection with Frame-wise Classifier
• Data-Efficient Framework for Real-world Multiple Sound Source 2D Localization
• DcaseNet: An integrated pretrained deep neural network for detecting and classifying acoustic scenes and events
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification
• Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices
• Ensemble of Discriminators for Domain Adaptation in Multiple Sound Source 2D Localization