A hybrid neural system for phonematic transformation

Igor T. Podolak, Seong Whan Lee, Andrzej Bielecki, Elzbieta Majkut

Research output: Chapter in Book/Report/Conference proceedingChapter

6 Citations (Scopus)

Abstract

Text-to-phoneme conversion is a common problem in speech processing. This can be done using a rule-based system or a neural network. In this paper we propose a solution to this problem using a modular hybrid system that uses basic rules to subdivide the original problem into easier tasks which are then solved by dedicated neural networks. Such a solution can be more rapidly constructed, and is easily extendable. A voting committee concept is used to enhance generalization abilities of the system.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages957-960
Number of pages4
Volume15
Edition2
Publication statusPublished - 2000

    Fingerprint

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Podolak, I. T., Lee, S. W., Bielecki, A., & Majkut, E. (2000). A hybrid neural system for phonematic transformation. In Proceedings - International Conference on Pattern Recognition (2 ed., Vol. 15, pp. 957-960)