Low-quality Fake Audio Detection through Frequency Feature Masking

Il Youp Kwak, Sunmook Choi, Jonghoon Yang, Yerin Lee, Soyul Han, Seungsang Oh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

The first Audio Deep Synthesis Detection Challenge (ADD 2022) competition was held which dealt with audio deepfake detection, audio deep synthesis, audio fake game, and adversarial attacks. Our team participated in track 1, classifying bona fide and fake utterances in noisy environments. Through exploratory data analysis,we found that noisy signals appear in similar frequency bands for given voice samples. If a model is trained to rely heavily on information in frequency bands where noise exists, performance will be poor. In this paper, we propose a data augmentation method, Frequency Feature Masking (FFM) that randomly masks frequency bands. FFM makes a model robust by not relying on specific frequency bands and prevents overfitting. We applied FFM and mixup augmentation on five spectrogram-based deep neural network architectures that performed well for spoofing detection using mel-spectrogram and constant Q transform (CQT) features. Our best submission achieved 23.8% in EER and ranked 3rd on track 1. To demonstrate the usefulness of our proposed FFM augmentation, we further experimented with FFM augmentation using ASVspoof 2019 Logical Access (LA) datasets.

Original languageEnglish
Title of host publicationDDAM 2022 - Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia
PublisherAssociation for Computing Machinery, Inc
Pages9-17
Number of pages9
ISBN (Electronic)9781450394963
DOIs
Publication statusPublished - 2022 Oct 14
Event1st International Workshop on Deepfake Detection for Audio Multimedia, DDAM 2022 - Lisboa, Portugal
Duration: 2022 Oct 14 → …

Publication series

NameDDAM 2022 - Proceedings of the 1st International Workshop on Deepfake Detection for Audio Multimedia

Conference

Conference1st International Workshop on Deepfake Detection for Audio Multimedia, DDAM 2022
Country/TerritoryPortugal
CityLisboa
Period22/10/14 → …

Bibliographical note

Funding Information:
This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (No. NRF-2022R1F1A1064273 and NRF-2020R1C1C1A01013020).

Publisher Copyright:
© 2022 Association for Computing Machinery.

Keywords

  • Audio deep synthesis
  • audio data augmentation
  • deep learning
  • frequency feature masking
  • low-quality audio

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'Low-quality Fake Audio Detection through Frequency Feature Masking'. Together they form a unique fingerprint.

Cite this