Articulatory Features for Describing Lexical Distinctions | Semantic Scholar

This paper comparatively analyzes the efficiency of two different neural networks, the Self-Organizing Maps (SOM) and the Time Organized Maps (TOM), applied for the recognition of the American English phonemes, and considers phonological features to represent the input data.

The apparently vast number of speech sounds found in the languages of the world turn out to be surface-level realisations of a limited number of combinations of a very small set of such features – some twenty or so, in current analyses.

It is suggested that the gestural approach clarifies the understanding of phonological development, by positing that prelinguistic units of action are harnessed into (gestural) phonological structures through differentiation and coordination.

Theoretical Implications Appendix: Full Syllables in SC References Index shows that connected speech and Other Dialects and Tone 3 Sandhi (T3S) have similar implications for language and literature.