ABSTRACT
Phonological feature structure is inherently multidimensional, and decades' worth of research in acoustic phonetics has documented both the complex mappings between features and associated acoustic cues as well as the prosodic modulation of these mappings. Most previous studies have focused on how the mean values of acoustic cues vary in complex ways across multiple phonological dimensions, relying on strong assumptions of statistical independence and/or homogeneity of variance across acoustic measures. The present study probes these assumptions by exploring the mapping between phonological voicing, place, and manner features and 8 acoustic cues from tokens of 14 English consonants produced in onset and coda position. Multivariate linear models exhibiting a variety of feature-cue mappings and between-cue statistical relationships were fit to this corpus of acoustic data. Model comparisons indicate that the best statistical description of the data requires pervasive interactions between features with respect to both the locations and the shapes of phonological categories. The implications of these results for work on the production and perception of phonological contrasts is discussed.
