A RECURRENT ERROR PROPAGATION NETWORK SPEECH RECOGNITION SYSTEM
Tony Robinson and Frank Fallside
November 1990
This paper describes a speaker independent phoneme and word recognition system based on a Recurrent Error Propagation Network (REPN) trained on the TIMIT database.
The REPN is a fully recurrent error propagation network trained by the propagation of the gradient signal backwards in time. A variation of the stochastic gradient descent procedure is used which updates the weights by an adaptive step size in the direction given by the sign of the gradient.
Phonetic context is stored internal to the network and the outputs are estimates of the probability that a given frame is part of a segment labelled with a context-independent phonetic symbol.
During recognition, a dynamic programming match is made to find the most probable string of symbols. This is done at a single level for phoneme recognition and at two levels for word recognition.
The phoneme recognition rate for all 61 TIMIT symbols is 70.0% correct (63.5% accuracy including insertion errors) and on a reduced 39 symbol set the recognition rate is 76.5% correct (69.8%). This compares favourably with the results of other methods, such as HMMs, on the same database (Lee and Hon, 1989; Levinson et al., 1989).
Analysis of the phoneme recognition results shows that information available from bigram and durational constraints is adequately handled within the network allowing for efficient parsing of the network output. For comparison, there is less computation involved in the resulting scheme than in a one-state-per-phoneme HMM system. This is demonstrated by applying the recogniser to the DARPA 1000-word Resource Management task. Parsing the network output to the word level with no grammar and no pruning can be carried out in faster than real time on a SUN 4/330 workstation.
If you have difficulty viewing files that end '.gz',
which are gzip compressed, then you may be able to find
tools to uncompress them at the gzip
web site.
If you have difficulty viewing files that are in PostScript, (ending
'.ps' or '.ps.gz'), then you may be able to
find tools to view them at
the gsview
web site.
We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.