Presentation 2008-12-10
Sudden noise reduction using dynamic speech feature model
Nobuyuki MIYAKE, Tetsuya TAKIGUCHI, Yasuo ARIKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a method for reducing sudden noise using a static and dynamic speech feature model. We have propoesed a method for reducing these noises using static feature model after the noisy frame is detected and what noise overlapped is classfied. But, the previous method has a problem that the noise reduction is not peroformed if the frame is not determined as noisy one although the frame has a noise. In this paper, we propose a noise reduction method using a dynamic feature model and last frame data in order to deal with such noisy frames. In our experiments, the proposed method achieved better performance for recognition of utterances overlapped by sudden noises than the previous method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) model-based noise reduction / dynamic feature model / sudden noise / speech recognition
Paper # NLC2008-56,SP2008-111
Date of Issue

Conference Information
Committee NLC
Conference Date 2008/12/2(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 Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Sudden noise reduction using dynamic speech feature model
Sub Title (in English)
Keyword(1) model-based noise reduction
Keyword(2) dynamic feature model
Keyword(3) sudden noise
Keyword(4) speech recognition
1st Author's Name Nobuyuki MIYAKE
1st Author's Affiliation Graduate School of Engineering, Kobe University()
2nd Author's Name Tetsuya TAKIGUCHI
2nd Author's Affiliation Graduate School of Engineering, Kobe University
3rd Author's Name Yasuo ARIKI
3rd Author's Affiliation Graduate School of Engineering, Kobe University
Date 2008-12-10
Paper # NLC2008-56,SP2008-111
Volume (vol) vol.108
Number (no) 337
Page pp.pp.-
#Pages 6
Date of Issue