The Development of the Speaker Independent ARM Continuous Speech Recognition System

Abstract

This memorandum describes the development of a speaker independent continuous speech recognition system based on phoneme level hidden Markov models. The system is configured to recognise continuously spoken airborne reconnaissance reports, a task which involves a vocabulary of approximately 500 words. On a test set of speech from 80 male subjects, the final system achieves a word accuracy of 74.1% with no explicit syntactic constraints.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1992
Accession Number
ADA247363

Entities

People

  • M. J. Russell

Organizations

  • Royal Signals and Radar Establishment

Tags

Communities of Interest

  • Advanced Electronics
  • Air Platforms
  • Space

DTIC Thesaurus Topics

  • Accuracy
  • Acoustic Signals
  • Airborne
  • Algorithms
  • Amplitude
  • Analyzers
  • Automated Speech Recognition
  • Decoding
  • Dictionaries
  • Hidden Markov Models
  • Markov Models
  • Materials
  • Models
  • Probability
  • Test And Evaluation
  • Test Sets
  • Training

Fields of Study

  • Computer science

Readers

  • Software Engineering
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation