Simulating Articulatory Trajectories with Phonological Feature Interpolation
This work addresses the challenge of computational modeling of speech production dynamics, but it is incremental as it focuses on a specific forward mapping step within a broader learning framework.
The paper tackled the problem of simulating articulatory trajectories from phonological features to model speech learning, achieving a Pearson correlation of 0.67 between generated trajectories and real articulatory data using an extended generative phonology feature set and linear interpolation.
As a first step towards a complete computational model of speech learning involving perception-production loops, we investigate the forward mapping between pseudo-motor commands and articulatory trajectories. Two phonological feature sets, based respectively on generative and articulatory phonology, are used to encode a phonetic target sequence. Different interpolation techniques are compared to generate smooth trajectories in these feature spaces, with a potential optimisation of the target value and timing to capture co-articulation effects. We report the Pearson correlation between a linear projection of the generated trajectories and articulatory data derived from a multi-speaker dataset of electromagnetic articulography (EMA) recordings. A correlation of 0.67 is obtained with an extended feature set based on generative phonology and a linear interpolation technique. We discuss the implications of our results for our understanding of the dynamics of biological motion.