I know that voice: Identifying the voice actor behind the voice

Lior Uzan, Lior Wolf

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

Abstract

Intentional voice modifications by electronic or nonelectronic means challenge automatic speaker recognition systems. Previous work focused on detecting the act of disguise or identifying everyday speakers disguising their voices. Here, we propose a benchmark for the study of voice disguise, by studying the voice variability of professional voice actors. A dataset of 114 actors playing 647 characters is created. It contains 19 hours of captured speech, divided into 29,733 utterances tagged by character and actor names, which is then further sampled. Text-independent speaker identification of the actors based on a novel benchmark training on a subset of the characters they play, while testing on new unseen characters, shows an EER of 17.1%, HTER of 15.9%, and rank-1 recognition rate of 63.5% per utterance when training a Convolutional Neural Network on spectrograms generated from the utterances. An I-Vector based system was trained and tested on the same data, resulting in 39.7% EER, 39.4% HTER, and rank-1 recognition rate of 13.6%.

Original languageEnglish
Title of host publicationProceedings of 2015 International Conference on Biometrics, ICB 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages46-51
Number of pages6
ISBN (Electronic)9781479978243
DOIs
StatePublished - 29 Jun 2015
Event8th IAPR International Conference on Biometrics, ICB 2015 - Phuket, Thailand
Duration: 19 May 201522 May 2015

Publication series

NameProceedings of 2015 International Conference on Biometrics, ICB 2015

Conference

Conference8th IAPR International Conference on Biometrics, ICB 2015
Country/TerritoryThailand
CityPhuket
Period19/05/1522/05/15

Fingerprint

Dive into the research topics of 'I know that voice: Identifying the voice actor behind the voice'. Together they form a unique fingerprint.

Cite this