Adversarial Domain Adaptation with Paired Examples for Acoustic Scene Classification on Different Recording Devices

10/18/2021
by   Stanisław Kacprzak, et al.
0

In classification tasks, the classification accuracy diminishes when the data is gathered in different domains. To address this problem, in this paper, we investigate several adversarial models for domain adaptation (DA) and their effect on the acoustic scene classification task. The studied models include several types of generative adversarial networks (GAN), with different loss functions, and the so-called cycle GAN which consists of two interconnected GAN models. The experiments are performed on the DCASE20 challenge task 1A dataset, in which we can leverage the paired examples of data recorded using different devices, i.e., the source and target domain recordings. The results of performed experiments indicate that the best performing domain adaptation can be obtained using the cycle GAN, which achieves as much as 66 improvement in accuracy for the target domain device, while only 6% relative decrease in accuracy on the source domain. In addition, by utilizing the paired data examples, we are able to improve the overall accuracy over the model trained using larger unpaired data set, while decreasing the computational cost of the model training.

READ FULL TEXT
research
04/30/2020

Unsupervised Domain Adaptation for Acoustic Scene Classification Using Band-Wise Statistics Matching

The performance of machine learning algorithms is known to be negatively...
research
08/17/2018

Unsupervised adversarial domain adaptation for acoustic scene classification

A general problem in acoustic scene classification task is the mismatche...
research
05/21/2021

Unsupervised Multi-Target Domain Adaptation for Acoustic Scene Classification

It is well known that the mismatch between training (source) and test (t...
research
11/06/2022

MiddleGAN: Generate Domain Agnostic Samples for Unsupervised Domain Adaptation

In recent years, machine learning has achieved impressive results across...
research
12/04/2018

Domain Mismatch Robust Acoustic Scene Classification using Channel Information Conversion

In a recent acoustic scene classification (ASC) research field, training...
research
07/31/2020

Relational Teacher Student Learning with Neural Label Embedding for Device Adaptation in Acoustic Scene Classification

In this paper, we propose a domain adaptation framework to address the d...
research
09/04/2019

Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification

Distribution mismatches between the data seen at training and at applica...

Please sign up or login with your details

Forgot password? Click here to reset