A Novel Noise Immune, Fuzzy Approach to Speaker Independent, Isolated Word Speech Recognition

Author

Halavati, Ramin ; Shouraki, Saeed Bagheri ; Razaghpour, Mina ; Tajik, Hossein ; Cholakian, Arpineh

Author_Institution

Sharif Univ. of Technol., Tehran

fYear

2006

fDate

24-26 July 2006

Firstpage

1

Lastpage

6

Abstract

This paper presents a novel approach to isolated word speech recognition using fuzzy modeling which is specifically designed to ignore noise. The task is based on conversion of speech spectrogram into a linguistic fuzzy description and comparison of this representation with fuzzy linguistic descriptions of words. The method is tested on single speaker and multiple speaker tests and the results are compared with a widely used speech recognition approach, showing much higher noise resistance.

Keywords

fuzzy set theory; gesture recognition; speech recognition; fuzzy modeling; fuzzy speech recognition; isolated word speech recognition; linguistic fuzzy description; noise immune speech recognition; noise resistance; speaker independent speech recognition; speech spectrogram; Acoustic noise; Design automation; Design engineering; Hidden Markov models; Humans; Immune system; Noise level; Speech enhancement; Speech recognition; Testing; Fuzzy Modeling; Speech Recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Automation Congress, 2006. WAC '06. World

Conference_Location

Budapest

Print_ISBN

1-889335-33-9

Type

conf

DOI

10.1109/WAC.2006.376025

Filename

4259941