DI-UMONS : Dépôt institutionnel de l’université de Mons

Recherche transversale
(titres de publication, de périodique et noms de colloque inclus)
2016-03-20 - Article/Dans un journal avec peer-review - Anglais - 5 page(s)

Dall Rasmus, Brognaux Sandrine , Richmond Korin, Valentini-Botinhao Cassia, Eje Henter Gustav, Hischberg Julia, Junichi Yamagishi, King Simon, "Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis" in IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings

  • Edition : IEEE. Institute of Electrical and Electronics Engineers
  • Codes CREF : Traitement du langage (DI4299)
  • Unités de recherche UMONS : Information, Signal et Intelligence artificielle (F105)
  • Instituts UMONS : Institut NUMEDIART pour les Technologies des Arts Numériques (Numédiart)
Texte intégral :

Abstract(s) :

(Anglais) Forced alignment for speech synthesis traditionally aligns a phoneme sequence predetermined by the front-end text processing system. This sequence is not altered during alignment, i.e., it is forced, despite possibly being faulty. The consistency assumption is the assumption that these mistakes do not degrade models, as long as the mistakes are consistent across training and synthesis. We present evidence that in the alignment of both standard read prompts and spontaneous speech this phoneme sequence is often wrong, and that this is likely to have a negative impact on acoustic models. A lattice- based forced alignment system allowing for pronunciation variation is implemented, resulting in improved phoneme identity accuracy for both types of speech. A perceptual evaluation of HMM-based voices showed that spontaneous models trained on this improved alignment also improved standard synthesis, despite breaking the consistency assumption.