Comparing phoneme and feature based speech recognition using artificial neural networks

An artificial neural network has been trained by the error backpropagation technique to recognise phonemes and words. The speech material was recorded by a male Swedish talker and was labelled by a ...

[1]  Arjen van Ooyen,et al.  Improving the convergence of the back-propagation algorithm , 1992, Neural Networks.

[2]  Stefanie Shattuck-Hufnagel,et al.  Implementation of a model for lexical access based on features , 1992, ICSLP.

[3]  Terrence J. Sejnowski,et al.  NETtalk: a parallel network that learns to read aloud , 1988 .

[4]  Mats Blomberg.  Adaptation to a speaker's voice in a speech recognition system based on synthetic phoneme references , 1991, Speech Commun..

[5]  M. Halle,et al.  Preliminaries to Speech Analysis: The Distinctive Features and Their Correlates , 1961 .

[6]  Hervé Bourlard,et al.  Phonetic context in hybrid HMM/MLP continuous speech recognition , 1991, EUROSPEECH.

[7]  James L. McClelland,et al.  Learning Subsequential Structure in Simple Recurrent Networks , 1988, NIPS.

[8]  Kjell Elenius,et al.  Acoustic-phonetic recognition of continuous speech by artificial neural networks , 1990 .

[9]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[10]  Mark Huckvale,et al.  Automatic phonetic feature labelling of continuous speech , 1989, EUROSPEECH.

[11]  Hervé Bourlard,et al.  Speech pattern discrimination and multilayer perceptrons , 1989 .

[12]  Kjell Elenius,et al.  Phoneme recognition with an artificial neural network , 1991, EUROSPEECH.

[13]  Frank Fallside,et al.  A recurrent error propagation network speech recognition system , 1991 .

[14]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[15]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .