An Evolutionary-based Generative Approach for Audio Data Augmentation

Silvan Mertes, Alice Baird, Dominik Schiller, Bjorn W. Schuller, Elisabeth Andre

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

In this paper, we introduce a novel framework to augment raw audio data for machine learning classification tasks. For the first part of our framework, we employ a generative adversarial network (GAN) to create new variants of the audio samples that are already existing in our source dataset for the classification task. In the second step, we then utilize an evolutionary algorithm to search the input domain space of the previously trained GAN, with respect to predefined characteristics of the generated audio. This way we are able to generate audio in a controlled manner that contributes to an improvement in classification performance of the original task. To validate our approach, we chose to test it on the task of soundscape classification. We show that our approach leads to a substantial improvement in classification results when compared to a training routine without data augmentation and training with uncontrolled data augmentation with GANs.

Original languageEnglish
Title of host publicationIEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728193205
DOIs
StatePublished - 21 Sep 2020
Externally publishedYes
Event22nd IEEE International Workshop on Multimedia Signal Processing, MMSP 2020 - Virtual, Tampere, Finland
Duration: 21 Sep 202024 Sep 2020

Publication series

NameIEEE 22nd International Workshop on Multimedia Signal Processing, MMSP 2020

Conference

Conference22nd IEEE International Workshop on Multimedia Signal Processing, MMSP 2020
Country/TerritoryFinland
CityVirtual, Tampere
Period21/09/2024/09/20

Keywords

  • data augmentation
  • evolutionary computing
  • generative adversarial networks
  • latent vector evolution
  • sound generation

Fingerprint

Dive into the research topics of 'An Evolutionary-based Generative Approach for Audio Data Augmentation'. Together they form a unique fingerprint.

Cite this