Ian Stavness

Articulatory Speech Synthesis


We have a new NSERC Strategic Project Grant on developing next-generation speech synthesis through simulations of the human voice, so-called articulatory speech synthesis. This project involves a team of investigators at the Universities of Toronto, Saskatchewan, and British Columbia creating new ways to image and measure speech production, new 3D computer simulations of vocal tract biomechanics, and state-of-the-art airflow based sound synthesis.

Our broader research activities in head & neck modeling are directed towards analysis of upper-airway dysfunctions, such as swallowing disorders (dysphagia), Obstructive Sleep Apnea (OSA) and computer-aided reconstructive head & neck surgery. This work involves advanced 3D biomechanical simulation with the ArtiSynth simulation toolkit.

We work closely with clinical collaborators across North America and Internationally. My group has recently developed a tracker tool for video fluoroscopy data that is being actively used by a number of clinical research groups.

Publications

Google Scholar Publications