Portal de Periódicos da CAPES

A model of prenatal acquisition of speech parameters.

1994; National Academy of Sciences; Volume: 91; Issue: 16 Linguagem: Inglês

10.1073/pnas.91.16.7473

1091-6490

Bradley Scott Seebach, Nathan Intrator, Philip Lieberman, Leon N. Cooper,

Speech Recognition and Synthesis

An unsupervised neural network model inductively acquires the ability to distinguish categorically the stop consonants of English, in a manner consistent with prenatal and early postnatal auditory experience, and without reference to any specialized knowledge of linguistic structure or the properties of speech. This argues against the common assumption that linguistic knowledge, and speech perception in particular, cannot be learned and must therefore be innately specified.