Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama’s voice using GAN, WaveNet and low-quality found data

Jaime Lorenzo-Trueba, Fuming Fang, Xin Wang, Isao Echizen, Junichi Yamagishi, Tomi Kinnunen

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

Abstract

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015 database. However, speech synthesis and voice conversion paradigms that are not considered in the ASVspoof2015 database are appearing. Such examples include direct waveform modelling and generative adversarial networks. We also need to investigate the feasibility of training spoofing systems using only low-quality found data. For that purpose, we developed a generative adversarial networkbased speech enhancement system that improves the quality of speech data found in publicly available sources. Using the enhanced data, we trained state-of-the-art text-to-speech and voice conversion models and evaluated them in terms of perceptual speech quality and speaker similarity. The results show that the enhancement models significantly improved the SNR of low-quality degraded data found in publicly available sources and that they significantly improved the perceptual cleanliness of the source speech without significantly degrading the naturalness of the voice. However, the results also show limitations when generating speech with the low-quality found data.
Original languageEnglish
Title of host publicationSpeaker Odyssey 2018
Subtitle of host publicationThe Speaker and Language Recognition Workshop
Place of PublicationLes Sables d’Olonne, France
PublisherISCA
Pages240-247
Number of pages8
DOIs
Publication statusPublished - 29 Jun 2018
EventThe Speaker and Language Recognition Workshop - Les Sables d’Olonne, France
Duration: 26 Jun 201829 Jun 2018
http://www.odyssey2018.org/

Publication series

Name
PublisherISCA
ISSN (Electronic)2312-2846

Conference

ConferenceThe Speaker and Language Recognition Workshop
Abbreviated titleSpeaker Odyssey 2018
Country/TerritoryFrance
CityLes Sables d’Olonne
Period26/06/1829/06/18
Internet address

Fingerprint

Dive into the research topics of 'Can we steal your vocal identity from the Internet?: Initial investigation of cloning Obama’s voice using GAN, WaveNet and low-quality found data'. Together they form a unique fingerprint.

Cite this