Article (Scientific journals)
ICE-Talk 2: Interface for Controllable Expressive TTS with perceptual assessment tool
Tits, Noé; El Haddad, Kevin; Dutoit, Thierry
2021In Software Impacts, 8 (100055)
Peer Reviewed verified by ORBi
 

Files


Full Text
PIIS2665963821000038_(1).pdf
Publisher postprint (1 MB)
Download

All documents in ORBi UMONS are protected by a user license.

Send to



Details



Abstract :
[en] In this paper, we present open-source (https://github.com/noetits/ICE-Talk) tools that facilitates the use of controllable TTS systems in experiments, towards the democratization of TTS systems across domains. ICE-Talk is a web-based GUI that allows the use of a TTS system with controllable parameters via a text field and a clickable 2D plot. It enables the study of latent spaces for controllable TTS. A tool to design a perceptual experiment is provided and consists of three steps: pre-synthesizing samples covering the 2D plot representing controllable dimensions, including this interface inside a template question, and integrate it in a Mechanical Turk system called turkle.
Disciplines :
Computer science
Library & information sciences
Author, co-author :
Tits, Noé  ;  Université de Mons > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
El Haddad, Kevin  ;  Université de Mons > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Dutoit, Thierry ;  Université de Mons > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle
Language :
English
Title :
ICE-Talk 2: Interface for Controllable Expressive TTS with perceptual assessment tool
Publication date :
01 May 2021
Journal title :
Software Impacts
eISSN :
2665-9638
Publisher :
Elsevier, Amsterdam, Netherlands
Volume :
8
Issue :
100055
Peer reviewed :
Peer Reviewed verified by ORBi
Research unit :
F105 - Information, Signal et Intelligence artificielle
Research institute :
R450 - Institut NUMEDIART pour les Technologies des Arts Numériques
Available on ORBi UMONS :
since 17 December 2021

Statistics


Number of views
35 (0 by UMONS)
Number of downloads
66 (0 by UMONS)

Scopus citations®
 
2
Scopus citations®
without self-citations
1
OpenCitations
 
1
OpenAlex citations
 
2

Bibliography


Similar publications



Contact ORBi UMONS