Effect of Reference Set Selection on Speaker Dependent Speech Recognition. Frame Compression in Isolated Word Recognition

Abstract

This paper describes an algorithm for compressing the spectral representation of an utterance along the time axis while keeping the main features intact. The goal of the algorithm is to save template storage space and to reduce the time required for recognition. For 8 speakers, 5 data sets each, the results indicated that we can save about 40% of the template space and 35% of the recognition time with only a slightly higher error rate.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 23, 1981
Accession Number
ADA104794

Entities

People

  • Fil Alleva
  • Raj Reddy
  • Zongge Li

Organizations

  • Carnegie Mellon University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Acoustics
  • Air Force
  • Algorithms
  • Automated Speech Recognition
  • Coefficients
  • Compression
  • Computer Science
  • Computers
  • Data Sets
  • Databases
  • Energy Levels
  • Errors
  • Fourier Analysis
  • Frequency
  • Recognition
  • Signal Processing
  • Word Recognition

Readers

  • Image Processing and Computer Vision.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • Space
  • Space - Space Objects