ATTRIBUTABLE WATERMARKING OF SPEECH GENERATIVE MODELS

Yongbaek Cho, Changhoon Kim, Yezhou Yang, Yi Ren

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

Abstract

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a solution for model attribution, i.e., the classification of synthetic contents by their source models via watermarks embedded in the contents. Building on past success of model attribution in the image domain, we discuss algorithmic improvements for generating user-end speech models that empirically achieve high attribution accuracy, while maintaining high generation quality. We show the tradeoff between attributability and generation quality under a variety of attacks on generated speech signals attempting to remove the watermarks, and the feasibility of learning robust watermarks against these attacks. Watermarked speech samples are available at https://attdemo.github.io/attdemofull.github.io.

Original languageEnglish (US)
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3069-3073
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Virtual, Online, Singapore
Duration: May 23 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityVirtual, Online
Period5/23/225/27/22

Keywords

  • Model Attribution
  • Speech Generation
  • Speech Watermarking
  • Voice Impersonation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'ATTRIBUTABLE WATERMARKING OF SPEECH GENERATIVE MODELS'. Together they form a unique fingerprint.

Cite this