Modeling Aspects of Multimodal Lithuanian Human - Machine Interface

  • Authors:
  • Rytis Maskeliunas

  • Affiliations:
  • Speech Research Lab., Kaunas University of Technology, Kaunas, Lithuania 51367

  • Venue:
  • Multimodal Signals: Cognitive and Algorithmic Issues
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper deals with modeling of multimodal human - machine interface. Multimodal access to the information retrieval system (computer) is possible by combining three different approaches: 1) Data input / retrieval by voice; 2) Traditional data input / retrieval systems; 3) Confirmation / rejection by recognizing and displaying human face expressions and emotions. A prototype of multimodal access for web application is presented by combining three modalities. Lithuanian language speech recognition experiment results on transcriptions and outcomes of discriminant analysis are presented.