Back to search

University of North Texas

Hopfield Networks as an Error Correcting Technique for Speech Recognition

Abstract

dc:description

I experimented with Hopfield networks in the context of a voice-based, query-answering system. Hopfield networks are used to store and retrieve patterns. I used this technique to store queries represented as natural language sentences and I evaluated the accuracy of the technique for error correction in a spoken question-answering dialog between a computer and a user. I show that the use of an auto-associative Hopfield network helps make the speech recognition system more fault tolerant. I also looked at the available encoding schemes to convert a natural language sentence into a pattern of zeroes and ones that can be stored in the Hopfield network reliably, and I suggest scalable data representations which allow storing a large number of queries.

Degree

thesis:*
Grantor dc:publisher
University of North Texas
Year dc:date
2004

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bireddy, Chakradhar
Contributors dc:contributor
  • Tarau, Paul
  • Brazile, Robert

Subjects

dc:subject × 6

Rights

dc:rights
Statement dc:rights
  • Use restricted to UNT Community (strictly enforced)
  • Copyright
  • Bireddy, Chakradhar
  • Copyright is held by the author, unless otherwise noted. All rights reserved.
Language dc:language
English

Identifiers

dc:identifier.*
Identifier
oclc: 55650397
https://digital.library.unt.edu/ark:/67531/metadc5551/
ark: ark:/67531/metadc5551

Chain of custody

source
Harvested from
University of North Texas
Base URL
digital.library.unt.edu/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Bireddy, Chakradhar. Hopfield Networks as an Error Correcting Technique for Speech Recognition. University of North Texas, 2004. https://doi.org/10.12794/metadc5551