MODULAR NEURAL NETWORK ARCHITECTURES

PDF

Authors
  1. Treurniet, W.C.
Corporate Authors
Communications Research Centre, Ottawa ONT (CAN)
Abstract
The currently preferred approaches for automatic recognition of sounds in continuous speech hypothesize the presence of words or sub-words, such as syllables or phonemes, on the basis of statistical models derived from training data. This paper is concerned with the ability of artificial neural networks to model phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base.
Report Number
DREA-TC-93-305-VOL-1-P-171 — @Conference Paper; CONTAINED IN 93-02664
Date of publication
01 Feb 1993
Number of Pages
37 (p171-207)
DSTKIM No
93-02655
CANDIS No
131314
Format(s):
Microfiche filmed at DSIS;Originator's fiche received by DSIS;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: