Stevens. Interpreting Acoustic Variability in Speech INVARIANCE AND VARIABILITY IN SPEECH: INTERPRETING ACOUSTIC EVIDENCE

The acoustic signal is the medium that is probably the most used in research on human speech production and perception and for characterizing the universal structures and units in terms of which the phonological forms of language are stored. Acoustic analysis of the speech signal also provides information which helps to characterize how particular distinctive features in a given language are implemented. Another use of acoustic analysis is to describe and to interpret differences in the way particular individuals produce an utterance. In this paper, examples are given to illustrate how interpretation of the acoustic signal or acoustic-articulatory models might provide insight into (1) possible defining acoustic/perceptual and articulatory correlates for universal distinctive features, (2) enhancements of these defining attributes in various contexts in particular languages, and (3) characteristics of this implementation by particular talkers. At the level of features, the possible defining acoustic and articulatory bases for the features [back] and [continuant] as revealed by acoustic/articulatory models are discussed. At the level of language differences, acoustic consequences of enhancement of the perceptual saliency of the voicing feature and of alveolar stops in English are described. Examples of talker differences that are discussed are: (1) individual characteristics of vocal-fold vibration, and (2) implementation of phrase boundaries. 1