Observatorio de I+D+i UPM

Memorias de investigación
Communications at congresses:
Development of a Genre-Dependent TTS System with Cross-Speaker Speaking-Style Transplantation
Year:2014
Research Areas
  • Electronic technology and of the communications,
  • Electric engineers, electronic and automatic (eil)
Information
Abstract
One of the biggest challenges in speech synthesis is the production of contextually-appropriate naturally sounding synthetic voices. This means that a Text-To-Speech system must be able to analyze a text beyond the sentence limits in order to select, or even modulate, the speaking style according to a broader context. Our current architecture is based on a two-step approach: text genre identification and speaking style synthesis according to the detected discourse genre. For the final implementation, a set of four genres and their corresponding speaking styles were considered: broadcast news, live sport commentaries, interviews and political speeches. In the final TTS evaluation, the four speaking styles were transplanted to the neutral voices of other speakers not included in the training database. When the transplanted styles were compared to the neutral voices, transplantation was significantly preferred and the similarity to the target speaker was as high as 78%.
International
Si
Congress
2nd International Workshop on Speech, Language and Audio in Multimedia (SLAM2014)
960
Place
Penang, Malaysia
Reviewers
Si
ISBN/ISSN
978-967-394-199-5
Start Date
11/09/2014
End Date
12/09/2014
From page
39
To page
42
Proceedings of the 2nd International Workshop on Speech, Language and Audio in Multimedia
Participants
  • Autor: Jaime Lorenzo Trueba (UPM)
  • Autor: Julian David Echeverry Correa (UPM)
  • Autor: Roberto Barra Chicote (UPM)
  • Autor: Javier Ferreiros Lopez (UPM)
  • Autor: Ascensión Gallardo Antolín (Universidad Carlos III de Madrid (UC3M))
  • Autor: Junichi Yamagishi (Centre for Speech Technology Research (CSTR), University of Edinburgh / National Institute of Informatics (NII), Tokio)
  • Autor: Simon King (Centre for Speech Technology Research (CSTR), University of Edinburgh)
  • Autor: Juan Manuel Montero Martinez (UPM)
Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Tecnología del Habla
  • Departamento: Ingeniería Electrónica
S2i 2020 Observatorio de investigación @ UPM con la colaboración del Consejo Social UPM
Cofinanciación del MINECO en el marco del Programa INNCIDE 2011 (OTR-2011-0236)
Cofinanciación del MINECO en el marco del Programa INNPACTO (IPT-020000-2010-22)