Clustering of Context Dependent Speech Units for Multilingual Speech Recognition

Abstract

The paper addresses the problem of designing a language independent phonetic inventory for the speech recognizers with multilingual vocabulary. A new clustering algorithm for the definition of multilingual set of triphones is proposed. The clustering algorithm bases on a definition of a distance measure for triphones defined as a weighted sum of explicit estimates of the context similarity on a monophone level. The monophone similarity estimation method based on the algorithm of Houtgast. The clustering algorithm is integrated in a multilingual speech recognition system based on HTK V2. 1.1. The experiments were based on the SpeechDat II databases1. So far, experiments included the Slovenian, Spanish and German 1000 FDB SpeechDat (H) databases. Experiments have shown that the use of clustering algorithm results in a significant reduction of the number of triphones with minor degradation of word accuracy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 2000
Accession Number
ADP010381

Entities

People

  • Bojan Imperl

Organizations

  • University of Maribor

Tags

DTIC Thesaurus Topics

  • Accuracy
  • Algorithms
  • Automated Speech Recognition
  • Clustering
  • Databases
  • Degradation
  • Identification
  • Inventory
  • Language
  • Pattern Recognition
  • Recognition
  • Spanish Language
  • Technical Information Centers
  • Transitions
  • Vocabulary
  • Word Recognition

Fields of Study

  • Computer science

Readers

  • Database Systems and Applications
  • Neural Network Machine Learning.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation