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

Recherche transversale
Rechercher
(titres de publication, de périodique et noms de colloque inclus)
2014-03-11 - Article/Dans un journal avec peer-review - Anglais - 16 page(s)

Picart Benjamin, Drugman Thomas, Dutoit Thierry , "Automatic Variation of the Degree of Articulation in New HMM-based Voices" in IEEE Journal of Selected Topics in Signal Processing, Pages 307 - 322

  • Edition : Institute of Electrical and Electronics Engineers, New York (NY)
  • Codes CREF : Sciences de l'ingénieur (DI2000), Electricité courants faibles (DI2500)
  • 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) This paper focuses on the automatic modification of the degree of articulation (hypo and hyperarticulation) of an existing standard neutral voice in the framework of HMM-based speech synthesis. Hypo and hyperarticulation refer to the production of speech respectively with a reduction and an increase of the articulatory efforts compared to the neutral style. Starting from a source speaker for which neutral, hypo and hyperarticulated speech data are available, statistical transformations are computed during the adaptation of the neutral speech synthesizer. These transformations are then applied to a new target speaker for which no hypo or hyperarticulated recordings are available. Four statistical methods are investigated, differing in the speaking style adaptation technique (model-space Linear Scaling LS vs. CMLLR) and in the speaking style transposition approach (phonetic vs. acoustic correspondence) they use. The efficiency of these techniques is assessed for the transposition of prosody and of filter coefficients separately. Besides we investigate which representation of the spectral envelope is the most suited for this purpose: MGC, LSP, PARCOR and LAR coefficients. Subjective evaluations are performed in order to determine which statistical transformation method achieves the highest performance in terms of segmental quality, reproduction of the articulation degree and speaker identity preservation. The most successful method is finally used for automatically modifying the degree of articulation of existing standard neutral voices.

Identifiants :
  • DOI : 10.1109/JSTSP.2014.2302742

Mots-clés :
  • (Anglais) Speech synthesis
  • (Anglais) HTS
  • (Anglais) Degree of articulation
  • (Anglais) Speaking style transposition
  • (Anglais) Voice quality
  • (Anglais) Expressive speech