SLAM: Automatic Stylization and Labelling of Speech Melody

This paper presents SLAM : a simple method for the automatic Stylization and Labelling of speech Melody. This main contributions over existing methods are : the alphabet of melodic contours is fully data-driven, an explicit time-frequency representation is used to derive complex melodic contours, and melodic contours can be determined over arbitrary prosodic/syntactic units. Additionally, the system can handle some specificities of spontaneous speech (e.g., multi speakers, speech turns and speech overlaps). A preliminary experiment conducted on 3 hours of spoken French indicates that a small number of contours is sufficient to explain most of the observed contours. The method can be easily adapted to other stressed languages. The implementation is open-source and freely available .