An Efficient A* Stack Decoder Algorithm for Continuous Speech Recognition with a Stochastic Language Model.

Abstract

The stack decoder is an attractive algorithm for controlling the acoustic and language model matching in a continuous speech recognizer. It implements a best-first tree search to find the best match to both the language model and the observed speech. A previous paper described a near-optimal admissible Viterbi A* search algorithms for use with non-cross-word acoustic models and no-grammar language models(1). This report extends this algorithm to include unigram language models and describes a modified version of the algorithm which includes the full (forward) decoder, corss-word acoustic models and longer-span language models. The resultant algorithm is not admissible, but has been demonstrated to be very efficient.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jul 18, 1991
Accession Number
ADA240745

Entities

People

  • D. B. Paul

Organizations

  • Massachusetts Institute of Technology

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Algorithms
  • Artificial Intelligence
  • Automated Speech Recognition
  • Computations
  • Equations
  • Errors
  • Grammars
  • Language
  • Mathematics
  • Models
  • Probability
  • Prototypes
  • Recognition
  • Resource Management
  • Transitions

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Computational Linguistics
  • Computer Programming and Software Development.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Machine Translation