Segment-Based Acoustic Models for Continuous Speech Recognition.

Abstract

This research aims to develop new and more accurate stochastic models for speaker-independent continuous speech recognition by extending previous work in segment-based modeling, by introducing a new hierarchical approach to representing intra-utterance statistical dependencies, and by developing language models that capture topic dependencies. These techniques, which have high computational costs because of the large search space associated with higher order models, are made feasible through a multi-pass search strategy that involves rescoring a constrained space given by an HMM decoding. We expect these different modeling techniques 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. The primary research efforts and results over the past quarter have included: experimentation with a new approach to continuous density parameter adaptation; improved the language modeling software to handle more general vocabularies and reduce storage requirements, and implemented a course-grained parallel training algorithm; extended the training algorithm for discrete distribution dependence trees (our model of intra-utterance correlation) to handle missing observations with the EM algorithm; implemented a dynamic programming algorithm for word lattice rescoring algorithm and demonstrated performance comparable to N-best rescoring with the SSM. (AN)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 30, 1994
Accession Number
ADA289971

Entities

People

  • J. R. Rohlicek
  • Mari Ostendorf

Organizations

  • Boston University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Channel Estimation
  • Discrete Distribution
  • Dynamic Programming
  • Electronic Mail
  • Language
  • Models
  • Probability
  • Random Variables
  • Recognition
  • Signal Processing
  • Software Design
  • Software Development
  • Statistics
  • Training
  • Vocabulary

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Computational Modeling and Simulation
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Space Objects