Computer Identification of Phonemes in Continuous Speech.

Abstract

An approach to computer identification of phoneme-sized sound elements in continuous speech is presented. Using a tape recorder as an input device, analog speech signals are digitized and fast Fourier transformed. The amplitudes of the transformed signals are combined in a logarithmic manner and the resulting 16 channels of data used as the input to a phoneme recognition scheme. A running crosscorrelation is performed with 47 stored phoneme prototypes. The locations of 'possible' phonemes are determined and one set of possible phonemes selected. The procedure was performed on three replicates of 45 isolated words and on three replicates of ten sentences.

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1976
Accession Number
ADA026018

Entities

People

  • Ralph W. Neyman

Organizations

  • Air Force Institute of Technology

Tags

DTIC Thesaurus Topics

  • Amplitude
  • Computers
  • Electronic Recording Systems
  • Identification
  • Prototypes
  • Recognition
  • Recording Systems
  • Tape Recorders

Readers

  • Approximation Theory.
  • Computer Science/Computer Engineering/Data Science/Digital Signal Processing.
  • Speech Processing/Speech Recognition.