Presentation 2013-07-25
Noise reduction based on fragmentary measurement of environmental noise
Kohei MACHIDA, Akinori ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a speech recognition method under noisy environments using multiple microphones based on asynchronous and intermittent observations. In this method, microphones placed at various locations in the room sometimes observe sounds, and clustering by GMM is performed to model the noise in the environment. Each of the clustered noise spectrum is subtracted from the input signal, and then the noise-reduced signals are decoded in parallel. Then, the final recognition result is determined by integrating all of the recognition results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) noise-robust speech recognition / multiple microphones / noise reduction / GMM
Paper # SP2013-53
Date of Issue

Conference Information
Committee SP
Conference Date 2013/7/18(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) Noise reduction based on fragmentary measurement of environmental noise
Sub Title (in English)
Keyword(1) noise-robust speech recognition
Keyword(2) multiple microphones
Keyword(3) noise reduction
Keyword(4) GMM
1st Author's Name Kohei MACHIDA
1st Author's Affiliation Graduate School of Engineering, Tohoku University()
2nd Author's Name Akinori ITO
2nd Author's Affiliation Graduate School of Engineering, Tohoku University
Date 2013-07-25
Paper # SP2013-53
Volume (vol) vol.113
Number (no) 161
Page pp.pp.-
#Pages 6
Date of Issue