Techniques to Achieve an Accurate Real-Time Large-Vocabulary Speech Recognition System

Abstract

In addressing the problem of achieving high-accuracy real-time speech recognition systems, we focus on recognizing speech from ARPA's 20,000-word Wall Street Journal (WSJ) task, using current UNIX workstations. We have found that our standard approach-using a narrow beam width in a viterbi search for simple discrete-density hidden Markov models (HMMs)-works in real time with only very low accuracy. Our most accurate algorithms recognize speech many times slower than real time. Our (yet unattained) goal is to recognize speech in real time at or near full accuracy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1994
Accession Number
ADA460505

Entities

People

  • Hy Murveit
  • John Butzberger
  • Peter Monaco
  • Vassilios Digalakis

Organizations

  • SRI International

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Automated Speech Recognition
  • Computational Complexity
  • Computations
  • Decoding
  • Errors
  • Grammars
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Natural Language Processing
  • Probability
  • Standards
  • Trees (Data Structures)
  • Vocabulary

Fields of Study

  • Computer science

Readers

  • Parallel and Distributed Computing.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Neural Networks