Ir directamente a la navegación principal Ir directamente a la búsqueda Ir directamente al contenido principal

Emotion identification for evaluation of synthesized emotional speech

  • Stefan Steidl
  • , Tim Polzehl
  • , H. Timothy Bunnell
  • , Ying Dou
  • , Prasanna Kumar Muthukumar
  • , Daniel Perry
  • , Kishore Prahallad
  • , Callie Vaughn
  • , Alan W. Black
  • , Florian Metze
  • Friedrich-Alexander University Erlangen-Nürnberg
  • Deutsche Telekom
  • Johns Hopkins University
  • Language Technologies Institute, Carnegie Mellon University
  • University of California at Los Angeles
  • International Institute of Information Technology Hyderabad
  • Oberlin College

Producción científicarevisión exhaustiva

10 Citas (Scopus)

Resumen

In this paper, we propose to evaluate the quality of emotional speech synthesis by means of an automatic emotion identification system. We test this approach using five different parametric speech synthesis systems, ranging from plain non-emotional synthesis to full re-synthesis of pre-recorded speech. We compare the results achieved with the automatic system to those of human perception tests. While preliminary, our results indicate that automatic emotion identification can be used to assess the quality of emotional speech synthesis, potentially replacing time consuming and expensive human perception tests.

Idioma originalEnglish
Título de la publicación alojadaProceedings of the 6th International Conference on Speech Prosody, SP 2012
EditorialTongji University Press
Páginas661-664
Número de páginas4
ISBN (versión impresa)9787560848693
EstadoPublished - 2012
Evento6th International Conference on Speech Prosody 2012, SP 2012 - Shanghai
Duración: 22 may 201225 may 2012

Serie de la publicación

NombreProceedings of the 6th International Conference on Speech Prosody, SP 2012
Volumen2

Conference

Conference6th International Conference on Speech Prosody 2012, SP 2012
País/TerritorioChina
CiudadShanghai
Período22/05/1225/05/12

Huella

Profundice en los temas de investigación de 'Emotion identification for evaluation of synthesized emotional speech'. En conjunto forman una huella única.

Citar esto