Adaptive environmental classification system for hearing aids

Authors

  • Luc Lamarche School of Information Technology and Engineering, University of Ottawa, 800 King Edward Ave., Ottawa, Ont. K1N 6N5
  • Wail Gueaieb School of Information Technology and Engineering, University of Ottawa, 800 King Edward Ave., Ottawa, Ont. K1N 6N5
  • Christian Giguère School of Information Technology and Engineering, University of Ottawa, 800 King Edward Ave., Ottawa, Ont. K1N 6N5
  • Tyseer Aboulnasr School of Information Technology and Engineering, University of Ottawa, 800 King Edward Ave., Ottawa, Ont. K1N 6N5

Keywords:

Cluster analysis, Feature extraction, Hearing aids, Learning systems, Merging, Adaptive environment, Adaptive learning process, Classification system, Merging environment

Abstract

An adaptive environmental classification system for hearing aids is introduced in which classes can be split and merged based on changes in the environment that the hearing aid is likely to encounter. The classification steps include information that distinguish different types of environments and the classification accuracy depending on the selection of features. The system stores the features in a buffer which is periodically processed to provide a single representative feature vector for the adaptive learning process. The adaptive learning phase begins when user fits the hearing aid and modifies the initial classification system to adapt to the user-specific environments. The general behavior of the adaptive classifier and the process of splitting and merging environment classes is represented by the squares in the center of each cluster represent the class centers.

Published

2007-09-01

How to Cite

1.
Lamarche L, Gueaieb W, Giguère C, Aboulnasr T. Adaptive environmental classification system for hearing aids. Canadian Acoustics [Internet]. 2007Sep.1 [cited 2021Apr.16];35(3):68-9. Available from: https://jcaa.caa-aca.ca/index.php/jcaa/article/view/1904

Issue

Section

Proceedings of the Acoustics Week in Canada

Most read articles by the same author(s)

1 2 3 4 > >>