Simulating Articulatory Trajectories with Phonological Feature Interpolation

TL;DR

This paper explores how to generate smooth articulatory trajectories from phonological features using interpolation techniques, aiming to model speech production dynamics and improve understanding of biological motion.

Contribution

It compares different interpolation methods on generative and articulatory phonology feature sets to produce realistic speech trajectories, advancing computational speech learning models.

Findings

Achieved a Pearson correlation of 0.67 with EMA data using generative features and linear interpolation.

Demonstrated the potential of feature interpolation for capturing co-articulation effects.

Provided insights into the dynamics of biological motion in speech production.

Abstract

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.