Exploring the Back-Propagation Network for Speech Applications

Abstract

Neural networks have sophisticated abilities for processing and filtering signals. In particular, Elman and Zipser demonstrated that the back- propagation network develops significant feature representations which may be useful for both segmenting and recognizing speech. Such networks might find applications in speech compression and/or normalization. The network's apparent potential for speech applications justifies further exploration, and this paper describes our work in progress.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1988
Accession Number
ADA197385

Entities

People

  • Doug Martin
  • Jeff Waters
  • Stephen Luse
  • Stephen Nunn

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Automated Speech Recognition
  • Batch Processing
  • Classification
  • Cognitive Science
  • Compression
  • Computer Science
  • Data Compression
  • Electrical Engineering
  • Identification
  • Learning
  • Load Monitoring
  • Neural Networks
  • New York
  • Notation
  • Recognition
  • Speech Compression

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks