A Novel Pattern Learning and Recognition Procedure Applied to the Learning of Vowels

Abstract

The ability of a set of simple predicates to capture characteristic patterns in a parametric representation of vowels in continuous speech was investigated with the aid of an efficient conjunctive pattern recognition and classification system. The results compare favorably with those produced by a cluster-based minimal Euclidean distance technique, run over the identical training and test samples. The predicates used are similar to auditory receptive fields.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1976
Accession Number
ADA025170

Entities

People

  • Frederick Hayes-roth
  • John Burge

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Amplitude
  • Classification
  • Coding
  • Computer Science
  • Computers
  • Decomposition
  • False Alarms
  • Frequency
  • Intervals
  • Learning
  • Pattern Recognition
  • Recognition
  • Security
  • Template Patterns
  • Universities

Readers

  • Artificial Intelligence
  • Regression Analysis.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks