Fast Search Algorithms for Connected Phone Recognition Using the Stochastic Segment Model

Abstract

In this paper we present methods for reducing the computation time of joint segmentation and recognition of phones using the Stochastic Segment Model (SSM). Our approach to the problem is twofold: first, we present a fast segment classification method that reduces computation by a factor of 2 to 4, depending on the confidence of choosing the most probable model. Second, we propose a Split and Merge segmentation algorithm as an alternative to the typical Dynamic Programming solution of the segmentation and recognition problem, with computation savings increasing proportionally with model complexity. Even though our current recognizer uses context-independent phone models, the results that we report on the TIMIT database for speaker independent joint segmentation and recognition are comparable to that of systems that use context information.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1990
Accession Number
ADA459580

Entities

People

  • J. R. Rohlicek
  • M. Ostendorf
  • V. Digalakis

Organizations

  • Boston University

Tags

Communities of Interest

  • Energy and Power Technologies
  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Accuracy
  • Algorithms
  • Artificial Intelligence
  • Boundaries
  • Computational Complexity
  • Computations
  • Computer Programming
  • Computer Vision
  • Databases
  • Dynamic Programming
  • Image Segmentation
  • Models
  • Probability
  • Recognition
  • Sequences
  • Test Sets

Fields of Study

  • Computer science

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Computational Modeling and Simulation
  • Speech Processing/Speech Recognition.