A hybrid neural system for phonematic transformation

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

Research output: Contribution to journalArticlepeer-review

6 Citations (Scopus)


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
Pages (from-to)957-960
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Issue number2
Publication statusPublished - 2000

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'A hybrid neural system for phonematic transformation'. Together they form a unique fingerprint.

Cite this