Statistical Modeling for Continuous Speech Recognition

Abstract

The authors' research into developing robust, high-performance continuous speech recognition systems for large-vocabulary tasks, such as battle management, has focused on the development of accurate mathematical models for the different phonemes that occur in English. The research performed in this project has been in three general areas: Hidden Markov Models, Stochastic Segment Models, and Rapid Speaker Adaptation. Hidden Markov models and stochastic segment models are two distinct methods of modeling phonetic coarticulation, i.e., the variation of phonemes in the context of other phonemes. The authors have tested the use of context-dependent hidden Markov models in BYBLOS, the BBN continuous speech recognition system, and report on word recognition accuracy in a 1000-word task domain. In contrast to hidden Markov modeling which models each part of a phoneme independently, stochastic segment modeling models each phoneme as a whole unit, and therefore has the promise of improved performance, as our preliminary experiments indicate.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1988
Accession Number
ADA192054

Entities

People

  • Alan Derr
  • M-w. Feng
  • O. Kimball
  • Robert E. Schwartz
  • Y-l. Chow

Organizations

  • BBN Technologies

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Computations
  • Databases
  • Dictionaries
  • Electronic Mail
  • Hidden Markov Models
  • Markov Models
  • Mathematical Models
  • Probabilistic Models
  • Probability
  • Probability Distributions
  • Recognition
  • Resource Management
  • Signal Processing
  • Test Sets
  • Word Recognition

Readers

  • Neural Network Machine Learning.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation