Hopfield Networks as an Error Correcting Technique for Speech Recognition Metadata

Metadata describes a digital item, providing (if known) such information as creator, publisher, contents, size, relationship to other resources, and more. Metadata may also contain "preservation" components that help us to maintain the integrity of digital files over time.


  • Main Title Hopfield Networks as an Error Correcting Technique for Speech Recognition


  • Author: Bireddy, Chakradhar
    Creator Type: Personal


  • Chair: Tarau, Paul
    Contributor Type: Personal
    Contributor Info: Major Professor
  • Committee Member: Brazile, Robert
    Contributor Type: Personal


  • Name: University of North Texas
    Place of Publication: Denton, Texas


  • Creation: 2004-05
  • Digitized: 2007-11-07


  • English


  • Content 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.


  • Library of Congress Subject Headings: Automatic speech recognition.
  • Library of Congress Subject Headings: Neural networks (Computer science)
  • Keyword: Hopfield network
  • Keyword: speech recognition
  • Keyword: error correction technique


  • Name: UNT Theses and Dissertations
    Code: UNTETD


  • Name: UNT Libraries
    Code: UNT


  • Rights Access: unt_strict
  • Rights License: copyright
  • Rights Holder: Bireddy, Chakradhar
  • Rights Statement: Copyright is held by the author, unless otherwise noted. All rights reserved.

Resource Type

  • Thesis or Dissertation


  • Text


  • OCLC: 55650397
  • Archival Resource Key: ark:/67531/metadc5551


  • Degree Name: Master of Science
  • Degree Level: Master's
  • Degree Discipline: Computer Science
  • Academic Department: Department of Computer Science
  • Degree Grantor: University of North Texas