Accession Number:

ADA272495

Title:

Application of a Back-Propagation Neural Network to Isolated-Word Speech Recognition

Descriptive Note:

Master's thesis,

Corporate Author:

NAVAL POSTGRADUATE SCHOOL MONTEREY CA

Personal Author(s):

Report Date:

1993-06-01

Pagination or Media Count:

44.0

Abstract:

The primary objective of this research is to explore how a back- propagation neural network BNN can be applied to isolated-word speech recognition. Simulation results show that a BNN provides an effective approach for small vocabulary systems. The recognition rate reaches 100 for a 5-word system and 94 for a 10-word system. The general techniques developed in this thesis can be further extended to other applications, such as sonar target recognition, missile seeking and tracking functions in modern weapon systems, and classification of underwater acoustic signals.

Subject Categories:

  • Linguistics
  • Computer Systems

Distribution Statement:

APPROVED FOR PUBLIC RELEASE