Advertisement

Diphone-Based Unit Selection for Catalan Text-to-Speech Synthesis

  • Roger Guaus i Teŕmens
  • Ignasi Iriondo Sanz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1902)

Abstract

This paper describes a Unit Selection system based on diphones that was developed by the Speech Technology Group of the Enginyeria Arquitectura La Salle School, Universitat Ramon Llull. This system works with a PSOLA synthesiser for Catalan language which is used in an Oral Synthesised Message Editor (EMOVS) and Windows applications developed using Microsoft SAPI. Some common questions about Unit Selection are formulated in order to find solutions and achieve a better segmental speech quality.

Keywords

Speech Synthesis Speech Quality Database Size Synthetic Speech Unit Selection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Guaus, R., Oliver, J., Moure, H., Iriondo, I., Martí J.: Síntesis de voz por concatenación de unidades: Mejoras en la calidad segmental. Tecniacústica 98, Lisboa (1998) 123–125.Google Scholar
  2. 2.
    Guaus, R. Oliver, J., Gudayol, F., Martí, J.: Síntesis de voz utilizando difonemas: Uniones entre vocales. SEPLN 97, Madrid (1997) 234–456.Google Scholar
  3. 3.
    Guaus, R.: Implementació i millores dún sistema de síntesi de veu d’alta qualitat utilitzant PSOLA. Projecte final de Carrera, ETSETB, Universitat Politècnica de Catalunya, Barcelona (1999).Google Scholar
  4. 4.
    Black, A.W.: Optimizing Selection of Units from Speech Databases for Concatenative Synthesis. Eurospeech’ 95, Madrid (1995).Google Scholar
  5. 5.
    Conkie, A.: Robust Unit Selection System for Speech Synthesis Joint Meeting of ASA, EAA and DAGA, Berlin (March 1999).Google Scholar
  6. 6.
    Beutnagel, M., Conkie, A., Schoeter, J., Stylianou, Y., Sydral, A.: The AT&T Next-Gen TTS System. Joint Meeting of ASA, EAA and DAGA, Berlin (March 1999).Google Scholar
  7. 7.
    Beutnagel, M., Conkie, A., Sydral, K.: Diphone Synthesis using Unit Selection. 3rd ESCA/COCOSDA Workshop on speech synthesis. Jenolan Caves, Austalia (November 1998).Google Scholar
  8. 8.
    Beutnagel, M., Conkie: Interaction of Units in a Unit Selection Database. EUROSPEECH’ 99, Budapest, Hungary (September 1999).Google Scholar
  9. 9.
    Avui Catalan newspaper URL: http://www.avui.com.

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Roger Guaus i Teŕmens
    • 1
  • Ignasi Iriondo Sanz
    • 1
  1. 1.Secció de Tecnologies de la Parla, Dept. de Comunicacions i Teoria del Senyal Enginyeria Arquitectura La SalleUniversitat Ramon LlullBarcelona

Personalised recommendations