Automatic Classification of Phonation Types in Spontaneous Speech: Towards a New Workflow for the Characterization of Speakers’ Voice Quality

Anaïs Chanclu (1) , Imen Ben Amor (1) , Cédric Gendrot (2) , Emmanuel Ferragne (2) , Jean-François Bonastre (1)

1 LIA - Laboratoire Informatique d'Avignon
2 LPP - LPP - Laboratoire de Phonétique et Phonologie - UMR 7018

Voice quality is known to be an important factor for the characterization of a speaker's voice, both in terms of physiological features (mainly laryngeal and supralaryngeal) and of the speaker's habits (sociolinguistic factors). This paper is devoted to one of the main components of voice quality: phonation type. It proposes neural representations of speech followed by a cascade of two binary neural network-based classifiers, one dedicated to the detection of modal and nonmodal vowels, and one for the classification of nonmodal vowels into creaky and breathy types. This approach is evaluated on the spontaneous part of the PTSVOX database, following an expert manual labelling of the data by phonation type. The results of the proposed classifiers reaches on average 85 % accuracy at the framelevel and up to 95 % accuracy at the segment-level. Further research is planned to generalize the classifiers on more contexts and speakers, and thus pave the way for a new workflow aimed at characterizing phonation types.

Mots clés: voice quality; speaker characterization; phonation type classification; neural network; explainability

Domaines: Informatique et langage [cs.CL]

Anaïs Chanclu, Imen Ben Amor, Cédric Gendrot, Emmanuel Ferragne, Jean-François Bonastre. Automatic Classification of Phonation Types in Spontaneous Speech: Towards a New Workflow for the Characterization of Speakers’ Voice Quality. Interspeech 2021, Aug 2021, Brno, Czech Republic. pp.1015-1018, ⟨10.21437/Interspeech.2021-1765⟩. ⟨hal-03334492⟩