Improvements in the BYBLOS Continuous Speech Recognition System

Abstract

The objective of this research was to develop accurate mathematical models of speech sounds for the purpose of large-vocabulary continuous speech recognition. The research focussed on three areas: developing better speech models to improve recognition accuracy, exploring new techniques for speaker-independent training, and developing speaker adaptation techniques that allow system use with a minimum of training. The work was performed within the BBN BYBLOS speech recognition system, which is based on the use of phonetic hidden Markov models. As a result of several model improvements, we have succeeded in decreasing the word rate by a factor of four for speaker-dependent and speaker- independent recognition. In speaker-independent recognition, we developed a new training paradigm in which we record speech from only a dozen speakers instead of the traditional approach of recording more than a hundred speakers. The same approach has been shown to be useful for effective speaker adaptation with only two minutes of speech training.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1990
Accession Number
ADA230126

Entities

People

  • C. Barry
  • F. Kubala
  • J. Makhoul
  • Robert E. Schwartz
  • S. Austin

Organizations

  • BBN Technologies

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Data Science
  • Databases
  • Discriminant Analysis
  • Hidden Markov Models
  • Information Science
  • Language
  • Markov Models
  • Mathematical Models
  • Probability
  • Resource Management
  • Signal Processing
  • Statistical Algorithms
  • Statistics
  • Steady State
  • Training
  • Word Recognition

Readers

  • Computational Modeling and Simulation
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation