Skip to main navigation Skip to search Skip to main content

Investigation into the Impact of Speaker Adversarial Perturbation on Speech Recognition

  • Chenyang Guo
  • , Liping Chen
  • , Kong Aik Lee
  • , Zhen Hua Ling
  • , Wu Guo

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

Abstract

Recent development in adversarial perturbation has shown its efficacy for voice privacy protection. This paper further explores the impact of speaker adversarial perturbation on speech in downstream automatic speech recognition (ASR) tasks. To be specific, the perturbation is generated by attacking a speaker embedding extractor in an untargeted manner and added to the original speech, resulting in the adversarial version. Additionally, we examine the efficacy of incorporating the supervision from an ASR model into the perturbation generation process. Experiments were conducted on the LibriSpeech dataset, where two ASR models with different levels of robustness were examined. Firstly, the results showed a decline in the ASR performance caused by the speaker adversarial perturbation, inferring the negative influence of the speaker perturbation on speech recognition. With the supervision of the ASR model during perturbation generation, its impact on speech recognition could be mitigated. Moreover, the ASR model with a lower robustness level provided a better constraint for generating perturbations, compared to the one with a higher robustness level. Audio samples can be found in (https://voiceprivacy.github.io/Speaker-Adversarial-Perturbation-Impact-on-ASR/).

Original languageEnglish
Title of host publicationMan-Machine Speech Communication - 19th National Conference, NCMMSC 2024, Proceedings
EditorsZhenhua Ling, Xie Chen, Askar Hamdulla, Liang He, Ya Li
PublisherSpringer Science and Business Media Deutschland GmbH
Pages191-199
Number of pages9
ISBN (Print)9789819610440
DOIs
Publication statusPublished - Dec 2024
Event19th National Conference on Man-Machine Speech Communication, NCMMSC 2024 - Urumqi, China
Duration: 15 Aug 202418 Aug 2024

Publication series

NameCommunications in Computer and Information Science
Volume2312 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference19th National Conference on Man-Machine Speech Communication, NCMMSC 2024
Country/TerritoryChina
CityUrumqi
Period15/08/2418/08/24

Keywords

  • Speaker adversarial perturbation
  • Speech recognition
  • Voice privacy protection

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Investigation into the Impact of Speaker Adversarial Perturbation on Speech Recognition'. Together they form a unique fingerprint.

Cite this