RECENT DEVELOPMENTS IN THE APPLICATION OF HIDDEN MARKOV MODELS IN SPEAKER-INDEPENDENT ISOLATED WORD RECOGNITION.

B. H. Juang, L. R. Rabiner, S. E. Levinson, M. M. Sondhi

Research output: Contribution to journalConference articlepeer-review

Abstract

Previous work on isolated word recognition based on hidden Markov models is extended by replacing the discrete symbol representation of the speech signal by a continuous Gaussian mixture density. In this manner the inherent quantization error introduced by the discrete representation is essentially eliminated. The resulting recognizer was tested on a vocabulary of the 10 digits across a wide range of talkers and test conditions and shown to have an error rate at least comparable to that of the best template recognizers and significantly lower than that of the discrete symbol hidden Markov model system. Several issues involved in the training of the continuous density models and in the implementation of the recognizer are discussed.

Original languageEnglish (US)
Pages (from-to)9-12
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
StatePublished - 1985
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'RECENT DEVELOPMENTS IN THE APPLICATION OF HIDDEN MARKOV MODELS IN SPEAKER-INDEPENDENT ISOLATED WORD RECOGNITION.'. Together they form a unique fingerprint.

Cite this