Presentation 1995/9/29
A Study of the Speech Recognition Utilizing the Fractal Properties of Vocal Sounds
SALVADOR SABANAL, MASAHIRO NAKAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this work, we shall propose a speech recognition model of words that utilizes the fractal properties of vocal sounds. Here the time-dependent multifractal dimensions (TDMFDs) of vocal sounds are used as recognition parameter. We find that TDMFDs and TDMFDs combined with the running power spectrum (RPS) and the time-dependent fractal dimension (TDFDs) by the critical exponent method(CEM) can achieve a higher recognition rate than the conventional RPS.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Vocal Sounds / Fractal Properties / Time-dependent Multifractal Dimensions / Neural Network / Recognition Rate
Paper # MBE95-72
Date of Issue

Conference Information
Committee MBE
Conference Date 1995/9/29(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To ME and Bio Cybernetics (MBE)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Study of the Speech Recognition Utilizing the Fractal Properties of Vocal Sounds
Sub Title (in English)
Keyword(1) Vocal Sounds
Keyword(2) Fractal Properties
Keyword(3) Time-dependent Multifractal Dimensions
Keyword(4) Neural Network
Keyword(5) Recognition Rate
1st Author's Name SALVADOR SABANAL
1st Author's Affiliation Department of Electrical Engineering, Faculty of Engineering, Nagaoka University of Technology()
2nd Author's Name MASAHIRO NAKAGAWA
2nd Author's Affiliation Department of Electrical Engineering, Faculty of Engineering, Nagaoka University of Technology
Date 1995/9/29
Paper # MBE95-72
Volume (vol) vol.95
Number (no) 285
Page pp.pp.-
#Pages 8
Date of Issue