Isolated Speech Recognition Using Artificial Neural Networks

Abstract

In this project Artificial Neural Networks are used as research tool to accomplish Automated Speech Recognition of normal speech. A small size vocabulary containing the words YES and NO is chosen. Spectral features using cepstral analysis are extracted per frame and imported to a feedforward neural network which uses a backpropagation with momentum training algorithm. The network is trained to recognize and classify the incoming words into the respective categories. The output from the neural network is loaded into a pattern search function, which matches the input sequence with a set of target word patterns. The level of variability in input speech patterns limits the vocabulary and affects the reliability of the network. The results from the first stage of this work are satisfactory and thus the application of artificial neural networks in conjunction with cepstral analysis in isolated word recognition holds promise.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 25, 2001
Accession Number
ADA409964

Entities

People

  • Fedra Adnani
  • Jun Yang
  • Prasad D. Polur
  • Rosalyn S. Hobson
  • Ruobing Zhou

Organizations

  • Virginia Commonwealth University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Biomedical Engineering
  • Classification
  • Coefficients
  • Digital Audio
  • Electrical Engineering
  • Engineering
  • Feature Extraction
  • Frequency
  • Human-Machine Interfaces
  • Identification
  • Intensive Care Units
  • Neural Networks
  • Numbers
  • Recognition
  • Sequences

Fields of Study

  • Computer science

Readers

  • Brain and Cognitive Science; Experimental Psychology; Cognitive Neuroscience
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks