Abstract for robinson_darpa92

Proc. ARPA Continuous Speech Recognition Workshop

RECURRENT NETS FOR PHONE PROBABILITY ESTIMATION

Tony Robinson

September 1992

This paper presents an overview of the use of recurrent networks for phone probability estimation in large vocabulary speech recognition. The current system is described and recent recognition results on the TIMIT and Resource Management tasks in multiple-speaker mode are presented. Results on the speaker-independent Resource Management task are presented for the first time.


(ftp:) robinson_darpa92.ps.Z (http:) robinson_darpa92.ps.Z
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) robinson_darpa92.pdf | (http:) robinson_darpa92.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.