The ATR/laryngeal connection and emergent features

‘Substance-free’ theories of phonology take two different approaches to eliminating phonetic information from phonological computations, positing either that distinctive features have phonetic content but phonological rules can manipulate them in arbitrary ways (Hale & Reiss 2003, 2008) or that features are based on phonological patterning and need not have any identifiable phonetic content at all (Blaho 2008; Samuels 2009). This chapter argues that the key insights of substance-free phonology can be maintained in a system that allows a limited role for phonetic substance. Methodologically, requiring that features have phonetic content and rules be formally natural limits the generative power of the system, forcing analysts to look more closely at apparently unnatural rules and classes, and precluding analyses based on spurious generalizations. At the same time, the fact that phonetic content does not always determine phonological patterning can be explained through underspecification based on contrast.