Servicio de Información Comunitario sobre Investigación y Desarrollo - CORDIS

High-Quality voice model for STatistical parametric speech Synthesis

Desde 2015-10-01 hasta 2017-12-31, proyecto cerrado | HQSTS Sitio web

Detalles del proyecto

Coste total:

EUR 183 454,80

Aportación de la UE:

EUR 183 454,80

Coordinado en:

United Kingdom

Convocatoria de propuestas:

H2020-MSCA-IF-2014See other projects for this call

Régimen de financiación:

MSCA-IF-EF-ST - Standard EF

Objetivo

Deliverables

Deliverables not available

Publications

  • A Pulse Model in Log-domain for a Uniform Synthesizer
    Author(s): Gilles Degottex Pierre Lanchantin Mark Gales
    Published in: Proc. 9th Speech Synthesis Workshop (SSW9), 2016. 
  • Integrated speaker-adaptive speech synthesis
    Author(s): Moquan Wan Gilles Degottex Mark Gales
    Published in: Proc. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2017. 
  • Light Supervised Data Selection, Voice Quality Normalized Training and Log Domain Pulse Synthesis
    Author(s): Gilles Degottex Pierre Lanchantin Mark Gales
    Published in: Proc. Blizzard Challenge 2017, 2017. 
  • A Log Domain Pulse Model for Parametric Speech Synthesis
    Author(s): Gilles Degottex, Pierre Lanchantin, Mark Gales
    Published in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, issue 26/1, 2018. Page(s) 57-70.  ISSN: 2329-9290
    DOI: 10.1109/TASLP.2017.2761546

Coordinador

THE CHANCELLOR MASTERS AND SCHOLARS OF THE UNIVERSITY OF CAMBRIDGE
United Kingdom

Aportación de la UE: EUR 183 454,80


TRINITY LANE THE OLD SCHOOLS
CB2 1TN CAMBRIDGE
United Kingdom
Activity type: Higher or Secondary Education Establishments

Contact the organisation

Síganos en: RSS Facebook Twitter YouTube Gestionado por la Oficina de Publicaciones de la UE Arriba