Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units

L. Deng, J. Wu, H. Sameti

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

In this paper we provide a formal description of a speech recognizer designed on the basis of elaborate articulatory timing that is asynchronous across the multiple articulatory-feature dimensions. Three recently improved critical components of the recognizer are described in detail. Evaluation results, obtained from a standard TIMIT phonetic recognition task confined within the N-best rescoring scenario, are reported on comparative performances between the new feature-based recognizer and a recognizer using the conventional context-dependent triphone units. The results demonstrate an overall superior quality of the rescored N-best list from the feature-based recognizer over that from the triphone-based recognizer. Greater performance improvements are observed as the top number of candidate sentences increases.

Original languageEnglish
Pages (from-to)385-388
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
Publication statusPublished - Jan 1 1995
Externally publishedYes
EventProceedings of the 1995 20th International Conference on Acoustics, Speech, and Signal Processing. Part 1 (of 5) - Detroit, MI, USA
Duration: May 9 1995May 12 1995

    Fingerprint

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this