Experimental Evaluation of Algorithms for Connected Speech Recognition Using Hidden Markov Models.

Abstract

Current Automatic Speech Recognition devices attempt to solve the connected word recognition problem by assuming that an unknown phrase is the output of a sequence of statistical word-models. Typically, these models are constructed using examples of words spoken in isolation; however, the acoustic patterns corresponding to words as they occur in fluent speech are quite different from those representing the same words spoken in isolation, and so the use in speech recognizers of models based on isolated utterances severely limits the performance of such devices. A method of extracting training utterances from fluent speech and constructing Hidden Markov Models (HMMs) from these templates, known as Embedded Training, is investigated here, in conjunction with a two-level algorithm for connected word recognition. The effects on recognition performance of various HMM training procedures are discussed, and experimental results are presented.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1987
Accession Number
ADA193651

Entities

People

  • Anneliese E. Cook

Organizations

  • Royal Signals and Radar Establishment

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Acoustic Properties
  • Acoustics
  • Algorithms
  • Automated Speech Recognition
  • Automatic
  • Boundaries
  • Computer Programming
  • Dynamic Programming
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Optimization
  • Probability
  • Recognition
  • Signal Processing
  • Word Recognition

Readers

  • Speech Processing/Speech Recognition.

Technology Areas

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