This paper introduces an interface that enables the real-time gesturalcontrol of intonation in phrases produced by a vocal synthesizer. Themelody and timing of a target phrase can be modified by tracing melodiccontours on the touch-screen of a mobile tablet. Envisioning this interfaceas a means for non-native speakers to practice the intonation of aforeign language, we present a pilot study where native and non-nativespeakers imitated the pronunciation of French phrases using their voiceand the interface, with a visual guide and without. Comparison of resultingF0 curves against the reference contour and a preliminary perceptualassessment of synthesized utterances suggest that for both non-nativeand native speakers, imitation with the help of a visual guide is comparablein accuracy to vocal imitation, and that timing control was a sourceof difficulty.
@inproceedings{xiao21_interspeech, title = {Prosodic Disambiguation Using Chironomic Stylization of Intonation with Native and Non-Native Speakers}, author = {Xiao Xiao and Nicolas Audibert and Grégoire Locqueville and Christophe d'Alessandro and Barbara Kuhnert and Claire Pillot-Loiseau}, year = {2021}, booktitle = {Interspeech 2021}, pages = {516--520}, doi = {10.21437/Interspeech.2021-182}, issn = {2958-1796},}Cite as:Xiao, X., Audibert, N., Locqueville, G., d'Alessandro, C., Kuhnert, B., Pillot-Loiseau, C. (2021) Prosodic Disambiguation Using Chironomic Stylization of Intonation with Native and Non-Native Speakers. Proc. Interspeech 2021, 516-520, doi: 10.21437/Interspeech.2021-182