Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/17242
Full metadata record
DC FieldValueLanguage
dc.contributor.authorThambipillai Srikanthan.-
dc.date.accessioned2009-06-02T01:54:16Z-
dc.date.available2009-06-02T01:54:16Z-
dc.date.copyright2008en_US
dc.date.issued2008-
dc.identifier.urihttp://hdl.handle.net/10356/17242-
dc.description.abstractModern voice authentication systems perform extremely well on large population high quality clean speech databases. While novel algorithms can be designed to provide performance and accuracy, the performance degrades rapidly in the presence of noise. Noise introduces a mismatch between the verification utterance and the speaker template which causes unpredictable scores leading to performance degradation. Our research attempts to address the problem of mismatch condition caused by additive noise. We have proposed novel algorithms for noise compensation in the speaker model domain and demonstrated their efficiency on TIMIT database corrupted with additive noise. Subsequently, we have combined the proposed algorithm with spectral subtraction method to further improve the performance of the authentication have been successfully translated to dedicated hardware architecture and prototyped on FPGA-based platforms.en_US
dc.format.extent39 p.en_US
dc.language.isoenen_US
dc.subjectDRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognitionen_US
dc.titleSeed funding for strategic research @ RTP (research manpower­)en_US
dc.typeResearch Report-
dc.contributor.schoolSchool of Computer Engineeringen_US
dc.description.reportnumberRGM 11/04en_US
item.grantfulltextrestricted-
item.fulltextWith Fulltext-
Appears in Collections:SCSE Research Reports (Staff & Graduate Students)
Files in This Item:
File Description SizeFormat 
ThambipillaiSrikanthan RGM11-04 SCE.pdf
  Restricted Access
1.4 MBAdobe PDFView/Open

Page view(s) 50

520
Updated on Nov 3, 2024

Download(s)

10
Updated on Nov 3, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.