Segment-Based Acoustic Models for Continuous Speech Recognition

Abstract

This paper presents an overview of the Boston University continuous word recognition system, which is based on the Stochastic Segment Model (SSM). The key components of the system described here include: a segment-based acoustic model that uses a family of Gaussian distributions to characterize variable length segments; a divisive clustering technique for estimating robust context-dependent models; and recognition using the N-best rescoring formalism, which also provides a mechanism for combining different knowledge sources (e.g. SSM and HMM scores). Results are reported for the speaker-independent portion of the Resource Management Corpus, for both the SSM system and a combined BU-SSM/BBN-HMM system.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 22, 1992
Accession Number
ADA259780

Entities

People

  • J. R. Rohlicek
  • Mari Ostendorf

Organizations

  • Boston University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Clustering
  • Computer Vision
  • Electronic Mail
  • Gaussian Distributions
  • Grammars
  • Hidden Markov Models
  • Markov Models
  • Probability
  • Recognition
  • Resource Management
  • Signal Processing
  • Systems Engineering
  • Test Sets
  • Universities
  • Word Recognition

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference