Please use this identifier to cite or link to this item:
https://hdl.handle.net/1959.11/15313
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Pervouchine, Vladimir | en |
dc.contributor.author | Leedham, Graham | en |
dc.contributor.author | Zhong, Haishan | en |
dc.contributor.author | Cho, David | en |
dc.contributor.author | Li, Haizhou | en |
local.source.editor | Editor(s): Pedro Encarnacao, Antonio Veloso | en |
dc.date.accessioned | 2014-06-27T13:24:00Z | - |
dc.date.issued | 2008 | - |
dc.identifier.citation | Proceedings of the First International Conference on Biomedical Electronics and Devices (BIOSIGNALS 2008), v.1, p. 220-223 | en |
dc.identifier.isbn | 9789898111180 | en |
dc.identifier.uri | https://hdl.handle.net/1959.11/15313 | - |
dc.description.abstract | Finding good features that represent speaker identity is an important problem in speaker recognition area. Recently a number of new and novel acoustic features have been proposed for speaker recognition. The researchers use different data sets and sometimes different classifiers to evaluate the features and compare them to the baselines such as MFCC or LPCC. However, due to different experimental conditions direct comparison of those features to each other is difficult or impossible. This paper presents a study of five new acoustic features recently proposed. The feature extraction has been performed on the same data (NIST~2001~SRE), and the same UBM-GMM classifier has been used. The results are presented as DET curves with equal error ratios indicated. Also, an SVM-based combination of GMM scores produced on different features has been made in hope that classifier fusion can result in higher speaker recognition accuracy. The results for different features as well as for their combinations are directly comparable to each other and to those obtained with the baseline MFCC features. | en |
dc.language | en | en |
dc.publisher | Institute for Systems and Technologies of Information, Control and Communication (INSTICC) | en |
dc.relation.ispartof | Proceedings of the First International Conference on Biomedical Electronics and Devices (BIOSIGNALS 2008) | en |
dc.title | Comparative Study of Several Novel Acoustic Features for Speaker Recognition | en |
dc.type | Conference Publication | en |
dc.relation.conference | BIOSIGNALS 2008: International Conference on Bio-inspired Systems and Signal Processing | en |
dc.subject.keywords | Image Processing | en |
dc.subject.keywords | Pattern Recognition and Data Mining | en |
dc.subject.keywords | Computer Vision | en |
local.contributor.firstname | Vladimir | en |
local.contributor.firstname | Graham | en |
local.contributor.firstname | Haishan | en |
local.contributor.firstname | David | en |
local.contributor.firstname | Haizhou | en |
local.subject.for2008 | 080106 Image Processing | en |
local.subject.for2008 | 080104 Computer Vision | en |
local.subject.for2008 | 080109 Pattern Recognition and Data Mining | en |
local.subject.seo2008 | 810199 Defence not elsewhere classified | en |
local.subject.seo2008 | 890299 Computer Software and Services not elsewhere classified | en |
local.subject.seo2008 | 810107 National Security | en |
local.profile.school | School of Science and Technology | en |
local.profile.school | Science and Technology | en |
local.profile.school | Science and Technology | en |
local.profile.email | cleedham@une.edu.au | en |
local.output.category | E2 | en |
local.record.place | au | en |
local.record.institution | University of New England | en |
local.identifier.epublicationsrecord | une-20100421-160534 | en |
local.date.conference | 28th - 31st January, 2008 | en |
local.conference.place | Funchal, Portugal | en |
local.publisher.place | United States of America | en |
local.format.startpage | 220 | en |
local.format.endpage | 223 | en |
local.identifier.volume | 1 | en |
local.contributor.lastname | Pervouchine | en |
local.contributor.lastname | Leedham | en |
local.contributor.lastname | Zhong | en |
local.contributor.lastname | Cho | en |
local.contributor.lastname | Li | en |
dc.identifier.staff | une-id:cleedham | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.profile.role | author | en |
local.identifier.unepublicationid | une:15529 | en |
dc.identifier.academiclevel | Academic | en |
local.title.maintitle | Comparative Study of Several Novel Acoustic Features for Speaker Recognition | en |
local.output.categorydescription | E2 Non-Refereed Scholarly Conference Publication | en |
local.relation.url | http://www.biosignals.biostec.org/Abstracts/2008/BIOSIGNALS_2008_Abstracts.htm | en |
local.conference.details | BIOSIGNALS 2008: International Conference on Bio-inspired Systems and Signal Processing, Funchal, Portugal, 28th - 31st January, 2008 | en |
local.search.author | Pervouchine, Vladimir | en |
local.search.author | Leedham, Graham | en |
local.search.author | Zhong, Haishan | en |
local.search.author | Cho, David | en |
local.search.author | Li, Haizhou | en |
local.uneassociation | Unknown | en |
local.year.published | 2008 | en |
local.date.start | 2008-01-28 | - |
local.date.end | 2008-01-31 | - |
Appears in Collections: | Conference Publication |
Files in This Item:
File | Description | Size | Format |
---|
Page view(s)
1,172
checked on Apr 7, 2024
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.