A Caltech Library Service

Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections

Unnikrishnan, K .P. and Hopfield, J. J. and Tank, D. W. (1992) Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections. Neural Computation, 4 (1). pp. 108-119. ISSN 0899-7667. doi:10.1162/neco.1992.4.1.108.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


The capability of a small neural network to perform speaker-independent recognition of spoken digits in connected speech has been investigated. The network uses time delays to organize rapidly changing outputs of symbol detectors over the time scale of a word. The network is data driven and unclocked. To achieve useful accuracy in a speaker-independent setting, many new ideas and procedures were developed. These include improving the feature detectors, self-recognition of word ends, reduction in network size, and dividing speakers into natural classes. Quantitative experiments based on Texas Instruments (TI) digit databases are described.

Item Type:Article
Related URLs:
URLURL TypeDescription
Tank, D. W.0000-0002-9423-4267
Additional Information:© 1992 Massachusetts Institute of Technology. Received 11 February 1991; accepted 15 July 1991. The TI connected digit data base was provided by the National Bureau of Standards. We wish to thank David Talkin for providing us the WAVES program and the Speech Research Department at Bell Labs for computer support. The work of J.J.H. at Caltech was supported in part by Office of Naval Research (Contract No. N00014-87-K-0377).
Funding AgencyGrant Number
Office of Naval ResearchN00014-87-K-0377
Issue or Number:1
Record Number:CaltechAUTHORS:UNNnc92
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:12332
Deposited By: Sydney Garstang
Deposited On:12 Nov 2008 22:51
Last Modified:08 Nov 2021 22:27

Repository Staff Only: item control page