A Neuro-Fuzzy Approach to Isolated Word Recognition.

Date of Submission

December 1997

Date of Award

Winter 12-12-1998

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Electronics and Communication Sciences Unit (ECSU-Kolkata)

Supervisor

Ray, Kumar Sankar (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

The dissertation deals with the applicatioin of fusion technology of artifi- cial neural network and fuzzy logic to the contradistinction of Bengali words by considering the first two formant frequencies of the embedded vowel patterns in them.To facilitate the said work we also give a new model of interpreta- tion to the multidimensional fuzzy reasoning and realize the same through a backpropagation type neural network,where the learning stage of the network uses fuzzy linguistic statements as input.Once learned, the nonfuzzy features can be classified by fuzzification of the desired features using fuzzy singleton and then feeding the ensuing fuzzy set to the recognition system followed by defuzzification of the result.The proposed model has been successfully tested for vowel recognition problem of some selected Bengali words.

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843180

Control Number

ISI-DISS-1997-48

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/6221

This document is currently not available here.

Share

COinS