Replay Spoofing Detection System for Automatic Speaker Verification Using Multi-Task Learning of Noise Classes

Hye Jin Shim, Jee Weon Jung, Hee Soo Heo, Sung Hyun Yoon, Ha Jin Yu

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

17 Scopus citations

Abstract

In this paper, we propose a replay attack spoofing detection system for automatic speaker verification using multi-task learning of noise classes. We define the noise that is caused by the replay attack as replay noise. We explore the effectiveness of training a deep neural network simultaneously for replay attack spoofing detection and replay noise classification. The multi-task learning includes classifying the noise of playback devices, recording environments, and recording devices as well as the spoofing detection. Each of the three types of the noise classes also includes a genuine class. The experiment results on the version 1.0 of ASVspoof2017 datasets demonstrate that the performance of our proposed system is improved by 30% relatively on the evaluation set.

Original languageEnglish
Title of host publicationProceedings - 2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages172-176
Number of pages5
ISBN (Electronic)9781728112299
DOIs
StatePublished - 24 Dec 2018
Event2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018 - Taichung, Taiwan, Province of China
Duration: 30 Nov 20182 Dec 2018

Publication series

NameProceedings - 2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018

Conference

Conference2018 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2018
Country/TerritoryTaiwan, Province of China
CityTaichung
Period30/11/182/12/18

Keywords

  • Anti-spoofing
  • Multi-task learning
  • Replay attack
  • Speaker verification
  • Spoofing detection

Fingerprint

Dive into the research topics of 'Replay Spoofing Detection System for Automatic Speaker Verification Using Multi-Task Learning of Noise Classes'. Together they form a unique fingerprint.

Cite this