On the use of a taxonomy of time-frequency morphologies for automatic speech recognition

  • Authors:

  • Renato De Mori;Mathew Palakal

  • Affiliations:

  • Concordia University, Department of Computer Science, Montreal, Quebec;Concordia University, Department of Computer Science, Montreal, Quebec

  • Venue:
  • IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 2
  • Year:
  • 1985

Quantified Score

Hi-index 0.00

Visualization

Abstract

A computer vision approach based on skeletonization and hierarchical description of speech patterns is proposed. Learniug hierarchical descriptions of phonetic events is discussed. Experimental results arc reported showing the power of the approach in the recognition of dipthongs in connected letters and digits.