A Comparative Study of Glottal Source Estimation Techniques

Thomas Drugman , Baris Bozkurt (1) , T. Dutoit (2)

1 Department of Electrical & Electronics Engineering
2 UMONS - University of Mons [Belgium]

Source-tract decomposition (or glottal ow estimation) is one of the basic problems of speech processing. For this, several techniques have been proposed in the literature. However studies comparing difierent approaches are almost nonexistent. Besides, experiments have been systematically performed either on synthetic speech or on sustained vowels. In this study we compare three of the main representative state-of-the-art methods of glottal ow estimation: closed-phase inverse _ltering, iterative and adaptive inverse _ltering, and mixed-phase decomposition. These techniques are _rst submitted to an objective assessment test on synthetic speech signals. Their sensitivity to various factors a_ecting the estimation quality, as well as their robustness to noise are studied. In a second experiment, their ability to label voice quality (tensed, modal, soft) is studied on a large corpus of real connected speech. It is shown that changes of voice quality are reected by signi_cant modi_cations in glottal feature distributions. Techniques based on the mixed-phase decomposition and on a closed-phase inverse _ltering process turn out to give the best results on both clean synthetic and real speech signals. On the other hand, iterative and adaptive inverse _ltering is recommended in noisy environments for its high robustness.

Mots clés: Source-tract Separation; Glottal Flow Estimation; Inverse Filtering; Mixed-Phase Decomposition; Voice Quality

Domaines: Linguistique

Thomas Drugman, Baris Bozkurt, T. Dutoit. A Comparative Study of Glottal Source Estimation Techniques. Computer Speech and Language, 2011, 26 (1), pp.20. ⟨10.1016/j.csl.2011.03.003⟩. ⟨hal-00770346⟩