Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

K. F. Leung, Hung Fat Frank Leung, H. K. Lam, S. H. Ling

Research output: Journal article publicationJournal articleAcademic researchpeer-review

20 Citations (Scopus)


This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.
Original languageEnglish
Pages (from-to)419-431
Number of pages13
JournalNeural Computing and Applications
Issue number4-5
Publication statusPublished - 1 May 2007


  • Fuzzy logic
  • Genetic algorithm
  • Neural network
  • Pattern recognition
  • Speech recognition

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Artificial Intelligence

Cite this