New Non-Supervised Learning Methods for Speaker Adaptation

Authors

  • Osamu KaKusho
  • Riichiro Mizoguchi

Abstract

An inter-related phoneme template system is proposed together with it’s two nonsupervised learning algorithms. Their efficiency is verified through some computer experiments of word recognition.

Additional Files

Published

2022-12-03

How to Cite

1.
KaKusho O, Mizoguchi R. New Non-Supervised Learning Methods for Speaker Adaptation. Canadian Acoustics [Internet]. 2022 Dec. 3 [cited 2024 Mar. 28];14(3 bis):99-100. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/3539

Issue

Section

Proceedings of the Acoustics Week in Canada