Recognition-Time Speaker Adaptation in a Tied-Mixture HMM Continuous Speech Recognizer.

Abstract

All speech recognition systems, whether speaker-independent or speaker-dependent, require large amounts of training data to estimate the model parameters and, generally, the more training data available, the better the recognition performance. To improve the recognition performance of a system for a new speaker without having to train entirely new models, adapting the existing models during the recognition process is a practical solution. This report describes an investigation into the subject of recognition-time speaker adaptation of a tied-mixture HMM recognition system, with the goal of implementing a system which adapts to a new speaker during the course of its usage.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 16, 1996
Accession Number
ADA319617

Entities

People

  • B. F. Necioglu
  • D. B. Paul

Organizations

  • Massachusetts Institute of Technology

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Air Force
  • Automated Speech Recognition
  • Hidden Markov Models
  • Information Operations
  • Markov Models
  • Massachusetts
  • Models
  • Natural Language Processing
  • Observation
  • Probability
  • Recognition
  • Resource Management
  • Standards
  • Test Sets
  • Training

Fields of Study

  • Engineering

Readers

  • Speech Processing/Speech Recognition.
  • Systems Analysis and Design

Technology Areas

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