Segment-Based Acoustic Models for Continuous Speech Recognition

Abstract

This research aims to develop new and more accurate acoustic models for speaker-independent continuous speech recognition, by extending previous work in segment-based modeling and by introducing a new hierarchical approach to representing intra-utterance statistical dependencies. These techniques, which are more costly than traditional approaches because of the large search space associated with higher order models, are made feasible through rescoring a set of HMM-generated N-best sentence hypotheses. We expect these different acoustic modeling methods to result in improved recognition performance over that achieved by current systems, which handle only frame-based observations and assume that these observations are independent given an underlying state sequence.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 05, 1993
Accession Number
ADA262968

Entities

People

  • J. R. Rohlicek
  • Mari Ostendorf

Organizations

  • Boston University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Ground and Sea Platforms

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Electronic Mail
  • Engineering
  • Gaussian Distributions
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Natural Language Processing
  • Neural Networks
  • Probability
  • Recognition
  • Resource Management
  • Signal Processing
  • Systems Engineering
  • Training

Fields of Study

  • Computer science

Readers

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

Technology Areas

  • AI & ML
  • Space
  • Space - Space Objects