Section: Software and Platforms

Xarticulators

Xarticulators software is intended to delineate contours of speech articulators in X-ray images, to construct articulatory models and to synthesize speech from X-ray films. This software provide tools to track contours automatically, semi-automatically or by hand, to make the visibility of contours easier, to add anatomical landmarks to speech articulators and to synchronize images together with the sound.

It also enables the construction of adaptable linear articulatory models from the X-ray images.

This year we particularly worked on the possibility of synthesizing speech from X-ray images. We thus substantially improved algorithms used to compute the centerline of the vocal tract in order to segment the vocal tract into elementary tubes approximating the propagation of a one-dimensional wave. We also developed time patterns used to synthesize sequences of voiceless consonants and vowels (VCV). In addition we also added the possibility of processing digitized manual delineation results made on sheet of papers in the seventies.