Show simple item record

dc.contributor.convenorSoon Hyob Kim and Dae Hee Youn
dc.contributor.authorShannon, BJ
dc.contributor.authorPaliwal, KK
dc.contributor.editorSoon Hyob Kim and Dae Hee Youn
dc.date.accessioned2017-05-03T13:01:01Z
dc.date.available2017-05-03T13:01:01Z
dc.date.issued2004
dc.date.modified2009-09-21T05:49:16Z
dc.identifier.urihttp://hdl.handle.net/10072/2122
dc.description.abstractProcessing of the speech signal in the autocorrelation domain in the context of robust feature extraction is based on the following two properties: 1) pole preserving property (the poles of a given (original) signal are preserved in its autocorrelation function), and 2) noise separation property (the autocorrelation function of a noise signal is confined to lower lags, while the speech signal contribution is spread over all the lags in the autocorrelation function, thus providing a way to eliminate noise by discarding lower-lag autocorrelation coefficients). In this paper, we use these properties to derive robust features for automatic speech recognition. We compute the magnitude spectrum of the one-sided higher-lag autocorrelation sequence, process it through a Mel filter bank and parameterise it in terms of Mel Frequency Cepstral Coefficients (MFCCs). Since the proposed method combines autocorrelation domain processing with Mel filter bank analysis, we call the resulting MFCCs, Autocorrelation Mel Frequency Cepstral Coefficients (AMFCCs). Recognition experiments are conducted on the Aurora II database and it is found that the AMFCC representation performs as well as the MFCC representation in clean conditions and provides more robust performance in the presence of background noise.
dc.description.peerreviewedYes
dc.description.publicationstatusYes
dc.languageEnglish
dc.language.isoeng
dc.publisherSunjin Printing Co.
dc.publisher.placeKorea
dc.publisher.urihttp://www.isca-speech.org/archive/interspeech_2004/i04_0129.html
dc.relation.ispartof0
dc.relation.ispartofconferencename8th International Conference on Spoken Language Processing
dc.relation.ispartofconferencetitle8th International Conference on Spoken Language Processing, ICSLP 2004
dc.relation.ispartofdatefrom2004-10-04
dc.relation.ispartofdateto2004-10-08
dc.relation.ispartoflocationJeju Island, Korea
dc.relation.ispartofpagefrom129
dc.relation.ispartofpageto132
dc.subject.fieldofresearchcode280206
dc.titleMFCC computation from magnitude spectrum of higher lag autocorrelation coefficients for robust speech recognition
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.facultyGriffith Sciences, Griffith School of Engineering
gro.date.issued2004
gro.hasfulltextNo Full Text
gro.griffith.authorPaliwal, Kuldip K.


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record