DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sungtak | ko |
dc.contributor.author | Ji, Mikyong | ko |
dc.contributor.author | Suh, Youngjoo | ko |
dc.contributor.author | Kim, HoiRin | ko |
dc.date.accessioned | 2011-03-29T06:32:07Z | - |
dc.date.available | 2011-03-29T06:32:07Z | - |
dc.date.created | 2012-02-06 | - |
dc.date.created | 2012-02-06 | - |
dc.date.issued | 2007-12 | - |
dc.identifier.citation | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, v.E90D, no.12, pp.2110 - 2114 | - |
dc.identifier.issn | 0916-8532 | - |
dc.identifier.uri | http://hdl.handle.net/10203/23070 | - |
dc.description.abstract | Recently, many techniques have been proposed to improve speaker identification in noise environments. Among these techniques, we consider the feature recombination technique for the multi-band approach in noise robust speaker identification. The conventional feature recombination technique is very effective in the band-limited noise condition, but in broad-band noise condition, the conventional feature recombination technique does not provide notable performance improvement compared with the full-band system. Even though the speech is corrupted by the broad-band noise, the degree of the noise corruption on each sub-band is different from each other. In the conventional feature recombination for speaker identification, all sub-band features are used to compute multiband likelihood score, but this likelihood computation does not use a merit of multi-band approach effectively, even though the sub-band features are extracted independently. Here we propose a new technique of sub-band likelihood computation with sub-band weighting in the feature recombination method. The signal to noise ratio (SNR) is used to compute the subband weights. The proposed sub-band-weighted likelihood computation makes a speaker identification system more robust to noise. Experimental results show that the average error reduction rate (ERR) in various noise environments is more than 24% compared with the conventional feature recombination-based speaker identification system. | - |
dc.language | English | - |
dc.language.iso | en_US | en |
dc.publisher | IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG | - |
dc.subject | MODELS | - |
dc.title | Noise robust speaker identification using sub-band weighting in multi-band approach | - |
dc.type | Article | - |
dc.identifier.wosid | 000252020000027 | - |
dc.identifier.scopusid | 2-s2.0-68249155208 | - |
dc.type.rims | ART | - |
dc.citation.volume | E90D | - |
dc.citation.issue | 12 | - |
dc.citation.beginningpage | 2110 | - |
dc.citation.endingpage | 2114 | - |
dc.citation.publicationname | IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | - |
dc.embargo.liftdate | 9999-12-31 | - |
dc.embargo.terms | 9999-12-31 | - |
dc.contributor.localauthor | Kim, HoiRin | - |
dc.contributor.nonIdAuthor | Kim, Sungtak | - |
dc.contributor.nonIdAuthor | Ji, Mikyong | - |
dc.contributor.nonIdAuthor | Suh, Youngjoo | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | feature recombination | - |
dc.subject.keywordAuthor | multi-band approach | - |
dc.subject.keywordAuthor | speaker identification | - |
dc.subject.keywordAuthor | sub-band likelihood | - |
dc.subject.keywordAuthor | sub-band weighting | - |
dc.subject.keywordPlus | MODELS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.