Hopfield Networks as an Error Correcting Technique for Speech Recognition

Access: Use of this item is restricted to the UNT Community
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.

Creator(s): Bireddy, Chakradhar
Creation Date: May 2004
Partner(s):
UNT Libraries
Collection(s):
UNT Theses and Dissertations
Usage:
Total Uses: 143
Past 30 days: 2
Yesterday: 0
Creator (Author):
Publisher Info:
Publisher Name: University of North Texas
Place of Publication: Denton, Texas
Date(s):
  • Creation: May 2004
  • Digitized: November 7, 2007
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:
Level: Master's
Discipline: Computer Science
Language(s):
Subject(s):
Keyword(s): Hopfield network | speech recognition | error correction technique
Contributor(s):
Partner:
UNT Libraries
Collection:
UNT Theses and Dissertations
Identifier:
  • OCLC: 55650397 |
  • ARK: ark:/67531/metadc5551
Resource Type: Thesis or Dissertation
Format: Text
Rights:
Access: Use restricted to UNT Community (strictly enforced)
License: Copyright
Holder: Bireddy, Chakradhar
Statement: Copyright is held by the author, unless otherwise noted. All rights reserved.