Quantifying articulatory variations across phonological environments: An atlas-based approach using dynamic magnetic resonance imaging.

Abstract

Identification and quantification of speech variations in velar production across various phonological environments have always been an interesting topic in speech motor control studies. Dynamic magnetic resonance imaging has become a favorable tool for visualizing articulatory deformations and providing quantitative insights into speech activities over time. Based on this modality, it is proposed to employ a workflow of image analysis techniques to uncover potential deformation variations in the human tongue caused by changes in phonological environments by altering the placement of velar consonants in utterances. The speech deformations of four human subjects in three different consonant positions were estimated from magnetic resonance images using a spatiotemporal tracking method before being warped via image registration into a common space-a dynamic atlas space constructed using four-dimensional alignments-for normalized quantitative comparisons. Statistical tests and principal component analyses were conducted on the magnitude of deformations, consonant-specific deformations, and internal muscle strains. The results revealed an overall decrease in deformation intensity following the initial consonant production, indicating potential muscle adaptation behaviors at a later temporal position in one speech utterance.