Unsupervised adversarial domain adaptation for acoustic scene classification (2018-08-17T00:00:00.000000Z)

TL;DR

The first method of unsupervised adversarial domain adaptation for acoustic scene classification is presented, which employs a model pre-trained on data from one set of conditions and by using data from other set of Conditions, which adapt the model in order that its output cannot be used for classifying the set of condition that input data belong to.

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.

Authors

Dmitriy Serdyuk

4 papers

Tuomas Virtanen

17 papers

Emre Çakir

3 papers

Unsupervised adversarial domain adaptation for acoustic scene classification

TL;DR

Abstract

Authors

References21 items

A multi-device dataset for urban acoustic scene classification

Domain Adaptation with Adversarial Training and Graph Embeddings

Multi-Adversarial Domain Adaptation

Adversarial Discriminative Domain Adaptation

Domain Separation Networks

Beyond Sharing Weights for Deep Domain Adaptation

Domain-Adversarial Training of Neural Networks

Adam: A Method for Stochastic Optimization

Unsupervised Domain Adaptation by Backpropagation

Autoencoder-based Unsupervised Domain Adaptation for Speech Emotion Recognition

Unsupervised Visual Domain Adaptation Using Subspace Alignment

Cross-Domain Facial Expression Recognition Using Supervised Kernel Mean Matching

Marginalized Denoising Autoencoders for Domain Adaptation

Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach

Covariate Shift by Kernel Mean Matching

GENERATIVE ADVERSARIAL NETS

Acoustic Scene Classification Based on Convolutional Neural Network Using Double Image Features

CLASSIFYING SHORT ACOUSTIC SCENES WITH I-VECTORS AND CNNS : CHALLENGES AND OPTIMISATIONS FOR THE 2017 DCASE ASC TASK

Acoustic Scene Classification Using Deep Convolutional Neural Network and Multiple Spectrograms Fusion

Convolutional Neural Networks with Binaural Representations and Background Subtraction for Acoustic Scene Classification

DCASE 2016 Acoustic Scene Classification Using Convolutional Neural Networks

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names