HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Hokkaido University Sustainability Weeks >
Sustainability Weeks 2009 >
2009 APSIPA Annual Summit and Conference >

Noise robust speech recognition using spectral subtraction and F0 information extracted by Hough transform

Files in This Item:
TP-P1-4.pdf155.41 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/39775

Title: Noise robust speech recognition using spectral subtraction and F0 information extracted by Hough transform
Authors: Yasui, Hideki Browse this author
Shinoda, Koichi Browse this author
Furui, Sadaoki Browse this author
Iwano, Koji Browse this author
Issue Date: 4-Oct-2009
Publisher: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference, International Organizing Committee
Journal Title: Proceedings : APSIPA ASC 2009 : Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference
Start Page: 631
End Page: 634
Abstract: We propose a noise robust speech recognition method based on combining novel features extracted from fundamental frequency (F0) information and spectral subtraction. F0 features have been shown to be effective in speech recognition in noisy environments. Recently, F0 features obtained by Hough transform were developed for concatenated digit recognition and significantly improved recognition performance of noisy speech. This paper proposes novel features based on Hough transform for large-vocabulary continuous speech recognition. In addition, spectral subtraction is applied before Hough transform to remove static noise. The proposed method was tested using the Japanese Newspaper Article Sentences (JNAS) database. Word accuracy was improved in all noise conditions, with the best absolute improvement being 2.6 points in percentage when station noise was added at 10 dB SNR.
Description: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference. 4-7 October 2009. Sapporo, Japan. Poster session: Automatic Speech Recognition (6 October 2009).
Conference Name: APSIPA ASC 2009: Asia-Pacific Signal and Information Processing Association, 2009 Annual Summit and Conference
2009年アジア太平洋信号情報処理連合学会アニュアルサミット・国際会議
Conference Place: Sapporo
Type: proceedings
URI: http://hdl.handle.net/2115/39775
Appears in Collections:北海道大学サステナビリティ・ウィーク2009 (Sustainability Weeks 2009) > 2009年アジア太平洋信号情報処理連合学会アニュアルサミット・国際会議 (2009 APSIPA Annual Summit and Conference)

Export metadata:

OAI-PMH ( junii2 , jpcoar_1.0 )

MathJax is now OFF:


 

 - Hokkaido University