Pattern recognition and feature selection for the development of a new artificial larynx

Megan J. Russell, David M. Rubin, Tshilidzi Marwala, Brian Wigdorowitz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

A palatometer system is used to read in tongue-palate contact patterns made during speech. The purpose is ultimately to develop an artificial larynx which will operate by determining the intended speech, and then synthesising the voice in a way that will hopefully mimic the user's prelaryngectomy sound. This paper describes the pattern recognition and feature selection techniques used to extract information from the tongue-palate contact patterns, and the effects the various methods have on the classification results. Training and testing datasets were constructed using 50 common words. The following feature extraction methods were used on the datasets: Principal Component Analysis, Fourier Descriptors, Correlation, Image Properties and Generic Fourier Descriptors. Once the features were extracted they were then used as input to a Multi-Layer Perceptron (MLP) Neural Network. The best MLP-based classification rate for the testing dataset was 78%, and this was achieved with the input of Correlation Coefficients. Further research will be conducted to try to improve these classification rates using a voting scheme, and possibly the application of word context.

Original languageEnglish
Title of host publicationWorld Congress on Medical Physics and Biomedical Engineering
Subtitle of host publicationImage Processing, Biosignal Processing, Modelling and Simulation, Biomechanics
PublisherSpringer Verlag
Pages736-739
Number of pages4
Edition4
ISBN (Print)9783642038815
DOIs
Publication statusPublished - 2009
EventWorld Congress on Medical Physics and Biomedical Engineering: Image Processing, Biosignal Processing, Modelling and Simulation, Biomechanics - Munich, Germany
Duration: 7 Sept 200912 Sept 2009

Publication series

NameIFMBE Proceedings
Number4
Volume25
ISSN (Print)1680-0737

Conference

ConferenceWorld Congress on Medical Physics and Biomedical Engineering: Image Processing, Biosignal Processing, Modelling and Simulation, Biomechanics
Country/TerritoryGermany
CityMunich
Period7/09/0912/09/09

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Pattern recognition and feature selection for the development of a new artificial larynx'. Together they form a unique fingerprint.

Cite this