Abstract for robinson_tr42

Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR42

PHONEME RECOGNITION FROM THE TIMIT DATABASE USING RECURRENT ERROR PROPAGATION NETWORKS

Tony Robinson and Frank Fallside

March 1990

This report describes a speaker independent phoneme recognition system based on the recurrent error propagation network recogniser described in (Robinson and Fallside, 1989; Fallside et al., 1990).

This recogniser employs a preprocessor which generates a range of types of output including bark scaled spectrum, energy and estimates of formant positions. The preprocessor feeds a fully recurrent error propagation network whose outputs are estimates of the probability that the given frame is part of a particular phonetic segment. The network is trained with a new variation on the stochastic gradient descent procedure which updates the weights by an adaptive step size in the direction given by the sign of the gradient. Once trained, a dynamic programming match is made to find the most probable symbol string of phonetic segments. The recognition rate is improved considerably when duration and bigram probabilities are used to constrain the symbol string.

A set of recognition results is presented for the trade off between insertion and deletion errors. When these two errors balance, the recognition rate for all 61 TIMIT symbols is 68.6%+-0.3% correct (62.5%+-0.4% including insertion errors) and on a reduced 39 symbol set the recognition rate is 75.1%+-0.2% correct (68.9%+-0.4%). This compares favourably with the results of other methods on the same database (Zue et al., 1989; Digalakis et al., 1989; Hataoka and Waibel, 1989; Lee and Hon, 1989; Levinson et al. 1989).


(ftp:) robinson_tr42.ps.Z (http:) robinson_tr42.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) robinson_tr42.pdf | (http:) robinson_tr42.pdf

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.