Tied Mixtures in the Lincoln Robust CSR

Abstract

HMM recognizers using either a single Gaussian or a Gaussian mixture per state have been shown to work fairly well for 1000-word vocabulary continuous speech recognition. However, the large number of Gaussians required to cover the entire English language makes these systems unwieldy for large vocabulary tasks. Tied mixtures offer a more compact way of representing the observation pdf's. We have converted our independent mixture systems to tied mixtures and have obtained mixed results: a 13% improvement in speaker-dependent recognition without cross-word triphone models, but no improvement in our speaker-dependent system with cross-word boundary triphone models or in our speaker-independent system. There is also a reduction in CPU requirements during recognition--but this is counter-balanced by an increase during training. This paper also includes a comment on the validity of the DARPA program's evaluation test system comparisons.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1989
Accession Number
ADA460569

Entities

People

  • Douglas B. Paul

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Binomials
  • Boundaries
  • Clustering
  • English Language
  • Grammars
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Natural Languages
  • Probability
  • Recognition
  • Resource Management
  • Standards
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Computer Science.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation