PRELIMINARY STUDY ON THE USE OF DEMISYLLABLES IN AUTOMATIC SPEECH RECOGNITION.

A. E. Rosenberg, L. R. Rabiner, S. E. Levinson, J. G. Wilpon

Research output: Contribution to journalConference article

Abstract

A speech recognition system is described for recognizing isolated words from reference templates created by concatenating demisyllables from a corpus of about 1000 demisyllables. The composition (in terms of demisyllables) of each reference word is specified in a lexicon with one or more entries for each word of the vocabulary. Experiments were carried out, using a 100-word vocabulary, to investigate the usefulness of such a representation and the effect on performance of some simple modifications in demisyllable specification and durations of reference patterns. Recognition accuracy of 97. 6% was obtained using

Original languageEnglish (US)
Pages (from-to)967-970
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume3
StatePublished - Jan 1 1981
Externally publishedYes
EventUnknown conference - Atlanta, Ga
Duration: Mar 30 1981Apr 1 1981

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this