Presentation 1997/6/20
Word Spotting based on the Generalized Hough Transform
Kouji SUGINO, Yutaka KOBAYASHI, Yasuhisa NIIMI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a method to detect particular speech segments as a key word from speech database. This approach, which is categorized as a template matching method, is aimed to identify speech segments without any models like HMM's. The Generalized Hough Transform(GHT) has been used to find arbitrary complex shapes on the image plane. We extended the GHT to be able to deal with three-dimensional shapes and applied it to the key word spotting in which a speech signal is represented as a spectral sequence. Then we conducted an experiment on the key word spotting, in which 15 key words were tried to extract from 450 utterances produced by 30 male speakers.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) spotting / template matching / Generalized Hough Transform / spectral sequence
Paper # SP97-23
Date of Issue

Conference Information
Committee SP
Conference Date 1997/6/20(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Word Spotting based on the Generalized Hough Transform
Sub Title (in English)
Keyword(1) spotting
Keyword(2) template matching
Keyword(3) Generalized Hough Transform
Keyword(4) spectral sequence
1st Author's Name Kouji SUGINO
1st Author's Affiliation Department of Electronics and Information Science Kyoto Institute of Technology()
2nd Author's Name Yutaka KOBAYASHI
2nd Author's Affiliation Department of Electronics and Information Science Kyoto Institute of Technology
3rd Author's Name Yasuhisa NIIMI
3rd Author's Affiliation Department of Electronics and Information Science Kyoto Institute of Technology
Date 1997/6/20
Paper # SP97-23
Volume (vol) vol.97
Number (no) 115
Page pp.pp.-
#Pages 6
Date of Issue