Presentation 2020-01-31
Basic Evaluation of Environmental Noise Removal for Improving Alarm Sound Source Classification Performance
Takeru Kadokura, Yuuki Hashizume, Yuusuke Kawakita, Hiroshi Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The authors are studying a method to classify ringing devices with high accuracy using neural networks from indoor alarm sounds for hearing impaired people and elderly people. In the room, there are many noises that affect the classification performance, such as the sound of a vacuum cleaner and a TV, as well as the alarm sound source. This paper describes the results of comparing the classification performance using the Spectral Subtraction method and the Denoising Autoencoder used for noise removal while changing the noise level.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / Classification / Noise Reduction / Spectral Subtraction / Denoising Autoencoder
Paper # SeMI2019-114
Date of Issue 2020-01-23 (SeMI)

Conference Information
Committee SeMI
Conference Date 2020/1/30(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Susumu Ishihara(Shizuoka Univ.)
Vice Chair Kazuya Monden(Hitachi) / Koji Yamamoto(Kyoto Univ.)
Secretary Kazuya Monden(Kyoto Univ.) / Koji Yamamoto(NTT DOCOMO)
Assistant Akira Uchiyama(Osaka Univ.) / Kenji Kanai(Waseda Univ.) / Masafumi Hashimoto(Osaka Univ.)

Paper Information
Registration To Technical Committee on Sensor Network and Mobile Intelligence
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Basic Evaluation of Environmental Noise Removal for Improving Alarm Sound Source Classification Performance
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) Classification
Keyword(3) Noise Reduction
Keyword(4) Spectral Subtraction
Keyword(5) Denoising Autoencoder
1st Author's Name Takeru Kadokura
1st Author's Affiliation Kanagawa Institute of Technology(Kanagawa Institute of Technology)
2nd Author's Name Yuuki Hashizume
2nd Author's Affiliation Kanagawa Institute of Technology(Kanagawa Institute of Technology)
3rd Author's Name Yuusuke Kawakita
3rd Author's Affiliation Kanagawa Institute of Technology(Kanagawa Institute of Technology)
4th Author's Name Hiroshi Tanaka
4th Author's Affiliation Kanagawa Institute of Technology(Kanagawa Institute of Technology)
Date 2020-01-31
Paper # SeMI2019-114
Volume (vol) vol.119
Number (no) SeMI-406
Page pp.pp.57-62(SeMI),
#Pages 6
Date of Issue 2020-01-23 (SeMI)