University of North Texas
Hopfield Networks as an Error Correcting Technique for Speech Recognition
Abstract
dc:descriptionI 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 × 6Rights
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