Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >

Please use this identifier to cite or link to this item:

This item has been viewed 133 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
King_Taylor_csl2000.pdf214.1 kBAdobe PDFView/Open
Title: Detection of Phonological Features in Continuous Speech using Neural Networks
Authors: King, Simon
Taylor, Paul
Issue Date: Oct-2000
Citation: Computer Speech and Language (2000) v. 14(4), pp. 333-353.
Publisher: Academic Press
Abstract: We report work on the first component of a two stage speech recognition architecture based on phonological features rather than phones. The paper reports experimentson three phonological feature systems: 1) the Sound Pattern of English (SPE) system which uses binary features, 2) a multi valued (MV) feature system which uses traditional phonetic categories such as manner, place etc, and 3) Government Phonology (GP) which uses a set of structured primes. All experiments used recurrent neural networks to perform feature detection. In these networks the input layer is a standard framewise cepstral representation, and the output layer represents the values of the features. The system effectively produces a representation of the most likely phonological features for each input frame. All experiments were carried out on the TIMIT speaker independent database. The networks performed well in all cases, with the average accuracy for a single feature ranging from 86% and 93%. We describe these experiments in detail, and discuss the justification and potential advantages of using phonological features rather than phones for the basis of speech recognition.
ISSN: 0885-2308
Appears in Collections:CSTR publications
Linguistics and English Language publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy