This paper proposes a new prosody annotation protocol specific to live sports commentaries. Two levels of annotation are defined with HMM-based speech synthesis in view. Local labels are assigned to all syllables and refer to accentual phenomena. Global labels classify sequences of words into five distinct sub-genres, defined in terms of valence and arousal. Our analysis shows that the labels are both related to a specific function and characterized by a distinct acoustic realization. The consideration of these constraints should allow for an automatic prediction of the labels both from the text or from the speech signal. The integration of this new annotation protocol within HMM-based speech synthesis shows promising results.
Brognaux, S., Picart, B., & Drugman, T. (2014). Synthèse de commentaires sportifs:intégration d’une annotation prosodique à deux niveauxdans un synthétiseur HMM. Nouveaux Cahiers de Linguistique Francaise, 31, 335. https://hdl.handle.net/2078.5/50546 (Original work published 2014)