Show simple item record

dc.contributor.authorTufekei, Zekeriya
dc.contributor.authorGowdy, John N.
dc.contributor.authorGurbuz, Sabri
dc.contributor.authorPatterson, Eric
dc.date.accessioned2021-02-12T18:52:39Z
dc.date.available2021-02-12T18:52:39Z
dc.date.issued2006
dc.identifier.issn0167-6393
dc.identifier.issn1872-7182
dc.identifier.urihttps://doi.org/10.1016/j.specom.2006.06.006
dc.identifier.urihttps://hdl.handle.net/11147/10733
dc.descriptionTufekci, Zekeriya/0000-0001-7835-2741en_US
dc.description.abstractInterfering noise severely degrades the performance of a speech recognition system. The Parallel Model Compensation (PMC) technique is one of the most efficient techniques for dealing with such noise. Another approach is to use features local in the frequency domain, such as Mel-Frequency Discrete Wavelet Coefficients (MFDWCs). In this paper, we investigate the use of PMC and MFDWC features to take advantage of both noise compensation and local features (MFDWCs) to decrease the effect of noise on recognition performance. We also introduce a practical weighting technique based on the noise level of each coefficient. We evaluate the performance of several wavelet-schemes using the NOISEX-92 database for various noise types and noise levels. Finally, we compare the performance of these versus Mel-Frequency Cepstral Coefficients (MFCCs), both using PMC. Experimental results show significant performance improvements for MFDWCs versus MFCCs, particularly after compensating the HMMs using the PMC technique. The best feature vector among the six MFDWCs we tried gave 13.72 and 5.29 points performance improvement, on the average, over MFCCs for -6 and 0 dB SNR, respectively. This corresponds to 39.9% and 62.8% error reductions, respectively. Weighting the partial score of each coefficient based on the noise level further improves the performance. The average error rates for the best MFDWCs dropped from 19.57% to 16.71% and from 3.14% to 2.14% for -6 dB and 0 dB noise levels, respectively, using the weighting scheme. These improvements correspond to 14.6% and 31.8% error reductions for -6 dB and 0 dB noise levels, respectively. (c) 2006 Elsevier B.V. All rights reserved.en_US
dc.language.isoengen_US
dc.publisherELSEVIERen_US
dc.relation.isversionof10.1016/j.specom.2006.06.006en_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectnoise robust ASRen_US
dc.subjectwaveleten_US
dc.subjectlocal featureen_US
dc.subjectfeature weightingen_US
dc.titleApplied mel-frequency discrete wavelet coefficients and parallel model compensation for noise-robust speech recognitionen_US
dc.typearticleen_US
dc.typearticleen_US
dc.relation.journalSpeech Communicationen_US
dc.contributor.departmentIzmir Isntitute of Technologyen_US
dc.identifier.volume48en_US
dc.identifier.issue10en_US
dc.identifier.startpage1294en_US
dc.identifier.endpage1307en_US
dc.identifier.wosWOS:000241586500006
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record