Edinburgh Research Explorer

Development of a Genre-Dependent TTS System with Cross-Speaker Speaking-Style Transplantation

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

  • Jaime Lorenzo-Trueba
  • Julian D. Echeverry-Correa
  • Roberto Barra-Chicote
  • Ruben San-Segundo
  • Javier Ferreiros
  • Ascension Gallardo-Antolin
  • Junichi Yamagishi
  • Simon King
  • Juan M. Montero

Related Edinburgh Organisations

Open Access permissions

Open

Documents

http://www.isca-speech.org/archive/slam_2014/slm4_039.html
Original languageEnglish
Title of host publication2nd International Workshop on Speech, Language and Audio in Multimedia (SLAM2014)
PublisherInternational Speech Communication Association
Publication statusPublished - 2014

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%.

Download statistics

No data available

ID: 20048062