Speech Recognition of Non-Native Speech Using Native and Non-Native Acoustic Models

Abstract

A speech recognition system is subjected to the speech of non-native speakers, using both native and non-native acoustic phone models. The problems involved with the mapping of phone set from the non- native to native language are investigated, and a detailed analysis of phone confusions is made. For Dutch speakers, British English acoustic models give the best word recognition results.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2000
Accession Number
ADP010382

Entities

People

  • David A. Van Leeuwen
  • Rosemary Orr

Tags

DTIC Thesaurus Topics

  • Artificial Intelligence
  • Automated Speech Recognition
  • Databases
  • Dictionaries
  • Information Systems
  • Language
  • Netherlands
  • Neural Networks
  • Probability
  • Recognition
  • Speech
  • Standards
  • Training
  • Universities
  • Vocabulary
  • Word Recognition
  • Workshops

Readers

  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation