caa a22 4500 386338779 CHVBK 20180307111741.0 cr unu---uuuuu 161130e198908 xx s 000 0 eng 10.1017/S0952675700001044 doi S0952675700001044 pii (NATIONALLICENCE)cambridge-10.1017/S0952675700001044 Lathroum Amanda Harvard University Feature encoding by neural nets [Elektronische Daten] [Amanda Lathroum] While the use of categorical features seems to be the appropriate way to express sound patterns within languages, these features do not seem adequate to describe the sounds actually produced by speakers. Examination of the speech signal fails to reveal objective, discrete phonological segments. Similarly, segments are not directly observable in the flow of articulatory movements, and vary slightly according to an individual speaker's articulatory strategies. Because of the lack of a reliable relationship between segments and speech sounds, a plausible transition from feature representation to the actual acoustic signal has proven elusive. This paper utilises a theory of information processing, known as PARALLEL DISTRIBUTED PROCESSING (PDP) NETWORKS (also called neural networks), to propose a model which begins to express this transition: translating the feature bundles indicated in a broad phonetic transcription into continuous, potentially variable articulator behaviour. Copyright © Cambridge University Press 1989 Phonology Cambridge University Press 6/2(1989-08), 305-316 0952-6757 6:2<305 1989 6 PHO https://doi.org/10.1017/S0952675700001044 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1017/S0952675700001044 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Lathroum Amanda Harvard University NATIONALLICENCE 773 0- Phonology Cambridge University Press 6/2(1989-08), 305-316 0952-6757 6:2<305 1989 6 PHO CC0 http://creativecommons.org/publicdomain/zero/1.0 nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-cambridge