Language Adaptive LVCSR Through Polyphone Decision Tree Specialization

Abstract

With the distribution of speech technology products all over the world, the fast and efficient portability to new target languages be comes a practical concern. In this paper we explore the relative effectiveness of porting multilingual recognition systems to new target languages with very limited adaptation data. For this purpose we introduce a polyphone decision tree specialization method. Several recognition results are presented based on mono- and multilingual recognizers developed in the framework of the project GlobalPhone which investigates LVCSR systems in 15 languages.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2000
Accession Number
ADP010393

Entities

People

  • A. Waibel
  • T. Schultz

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Clustering
  • Databases
  • Dictionaries
  • French Language
  • German Language
  • Identification
  • International Relations
  • Language
  • Markov Models
  • Models
  • Phonemes
  • Recognition
  • Specialization
  • Test Sets
  • Vocabulary

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Computational Linguistics
  • Immunology