Modelling Context Dependency in Acoustic-Phonetic and Lexical Representations

Abstract

In 1989, our group first reported on the development of SUMMIT, a segment-based speaker-independent continuous-speech recognition system [13] . The initial version of SUMMIT made use of fairly simple context-independent models for the lexical labels. Recently, we have begun to incorporate more complex models of lexical labels that take into account a variety of contextual factors. These changes, along with an improved corrective training procedure for adapting pronunciation arc weights and a larger set of training data, have resulted in the reduction of error rate by almost a factor of two on the Resource Management task.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1991
Accession Number
ADA460564

Entities

People

  • James Glass
  • Michael Phillips
  • Victor Zue

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Accounting
  • Algorithms
  • Automated Speech Recognition
  • Computer Science
  • Language
  • Machine Learning
  • Measurement
  • Natural Languages
  • Probability
  • Recognition
  • Resource Management
  • Signal Processing
  • Standards
  • Test Sets
  • Training
  • Word Recognition
  • Workshops

Readers

  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation
  • AI & ML - Neural Networks