基于LDOF准则的自适应高斯后端语种识别方法

TN912.34; 针对由语种类内多样性引起的测试样本和训练模型不匹配的问题,提出一种基于局部距离离群因子准则(LDOF,local distance-based outlier factor)的自适应高斯后端语种识别方法.定义LDOF准则,实现有效的参数寻优过程并动态地在多类语种训练集上挑选出与测试样本特性相近的训练样本,调整原高斯后端,进而得到改进的语种识别方法.在NIST LRE 2009的6个易混淆语种任务集上的实验结果表明,所提方法的等错误概率(EER,equal error rate)和平均检测代价有显著提升....

Full description

Saved in:
Bibliographic Details
Published in通信学报 Vol. 38; no. 4; pp. 17 - 24
Main Authors 叶中付, 戚婷, 李赛峰, 宋彦
Format Journal Article
LanguageChinese
Published 中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027 2017
数学工程与先进计算国家重点实验室,江苏无锡214125%中国科学技术大学信息科学技术学院,安徽合肥230027
中国科学技术大学信息科学技术学院,安徽合肥230027
Subjects
语种识别
类内多样性
language recognition
adaptive Gaussian back-end
自适应高斯后端
LDOF
inter-language variations
Online AccessGet full text
ISSN1000-436X
DOI10.11959/j.issn.1000-436x.2017096

Cover

Abstract TN912.34; 针对由语种类内多样性引起的测试样本和训练模型不匹配的问题,提出一种基于局部距离离群因子准则(LDOF,local distance-based outlier factor)的自适应高斯后端语种识别方法.定义LDOF准则,实现有效的参数寻优过程并动态地在多类语种训练集上挑选出与测试样本特性相近的训练样本,调整原高斯后端,进而得到改进的语种识别方法.在NIST LRE 2009的6个易混淆语种任务集上的实验结果表明,所提方法的等错误概率(EER,equal error rate)和平均检测代价有显著提升.
AbstractList TN912.34; 针对由语种类内多样性引起的测试样本和训练模型不匹配的问题,提出一种基于局部距离离群因子准则(LDOF,local distance-based outlier factor)的自适应高斯后端语种识别方法.定义LDOF准则,实现有效的参数寻优过程并动态地在多类语种训练集上挑选出与测试样本特性相近的训练样本,调整原高斯后端,进而得到改进的语种识别方法.在NIST LRE 2009的6个易混淆语种任务集上的实验结果表明,所提方法的等错误概率(EER,equal error rate)和平均检测代价有显著提升.
Abstract_FL In order to alleviate the mismatch in model between training and testing samples caused by inter-language variations,adaptive Gaussian back-end based on LDOF criterion was proposed for language recognition.The local distance-based outlier factor (LDOF) criterion was defined to find the appropriate model parameters and dynamically select the training data subset similar to the testing samples from multiple class training sets.Then original back-end was adjusted to obtain a more matched recognition model.Experimental results on NIST LRE 2009 easily-confused language data set show that proposed method achieves an obvious performance improvement on both the equal error rate (ERR)and average decision cost function.
Author 宋彦
戚婷
叶中付
李赛峰
AuthorAffiliation 中国科学技术大学信息科学技术学院,安徽合肥230027;中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027;数学工程与先进计算国家重点实验室,江苏无锡214125%中国科学技术大学信息科学技术学院,安徽合肥230027;中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027
AuthorAffiliation_xml – name: 中国科学技术大学信息科学技术学院,安徽合肥230027;中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027;数学工程与先进计算国家重点实验室,江苏无锡214125%中国科学技术大学信息科学技术学院,安徽合肥230027;中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027
Author_xml – sequence: 1
  fullname: 叶中付
– sequence: 2
  fullname: 戚婷
– sequence: 3
  fullname: 李赛峰
– sequence: 4
  fullname: 宋彦
BookMark eNo1jztLw1Acxe9QwVr7IRwcE__33esm1aoQ6NLBrdybh7RICkYxo4hYF0sHLeriKBgkg5P5PObRb2HwMR04HH7nnDXUCCehj9AGBhtjxdXW2B5FUWhjALAYFbFNAEtQooGa_97RKmpH0cgAx1QKoLiJtvOX7CubObv9Xj69yW-fyufravq2vLzKs_tl8lgs0nw-K5O0St_L17sqrTNJsfgsPh7W0UqgTyK__actNOjtDboHltPfP-zuOJbLJbWY0YQawgUBYjBlJpCYCKKkJ3VAXMOVKxWj2sXgex43HeJiXwSMd5SUrB7aQpu_2AsdBjo8Ho4n56dhXTg8i2Pzc5IBUPoNaRReEg
ClassificationCodes TN912.34
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.11959/j.issn.1000-436x.2017096
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Adaptive Gaussian back-end based on LDOF criterion for language recognition
EndPage 24
ExternalDocumentID txxb201704003
GrantInformation_xml – fundername: 数学工程与先进计算国家重点实验室开放基金资助项目(No.2015A15)The Open Project Program of the State Key Laboratory of Mathematical Engineering and Advanced Computing
  funderid: (2015A15)
GroupedDBID -0Y
2B.
4A8
92I
93N
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CUBFJ
GROUPED_DOAJ
PSX
TCJ
ID FETCH-LOGICAL-c573-4ba23b256202b134bf7126297d7af2cb59c7943ac10edd5b82c1e6f4589774513
ISSN 1000-436X
IngestDate Thu May 29 04:00:48 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 4
Keywords 语种识别
类内多样性
language recognition
adaptive Gaussian back-end
自适应高斯后端
LDOF
inter-language variations
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c573-4ba23b256202b134bf7126297d7af2cb59c7943ac10edd5b82c1e6f4589774513
PageCount 8
ParticipantIDs wanfang_journals_txxb201704003
PublicationCentury 2000
PublicationDate 2017
PublicationDateYYYYMMDD 2017-01-01
PublicationDate_xml – year: 2017
  text: 2017
PublicationDecade 2010
PublicationTitle 通信学报
PublicationTitle_FL Journal on Communications
PublicationYear 2017
Publisher 中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027
数学工程与先进计算国家重点实验室,江苏无锡214125%中国科学技术大学信息科学技术学院,安徽合肥230027
中国科学技术大学信息科学技术学院,安徽合肥230027
Publisher_xml – name: 数学工程与先进计算国家重点实验室,江苏无锡214125%中国科学技术大学信息科学技术学院,安徽合肥230027
– name: 中国科学技术大学语音及语言信息处理国家工程实验室,安徽合肥230027
– name: 中国科学技术大学信息科学技术学院,安徽合肥230027
SSID ssib051376031
ssj0002912165
ssib058759023
ssib001102965
ssib023646527
ssib023168036
ssib036439991
ssib050281523
ssib000968473
Score 2.1396744
Snippet TN912.34; 针对由语种类内多样性引起的测试样本和训练模型不匹配的问题,提出一种基于局部距离离群因子准则(LDOF,local distance-based outlier factor)的自适应高斯后端语...
SourceID wanfang
SourceType Aggregation Database
StartPage 17
Title 基于LDOF准则的自适应高斯后端语种识别方法
URI https://d.wanfangdata.com.cn/periodical/txxb201704003
Volume 38
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  issn: 1000-436X
  databaseCode: M~E
  dateStart: 19800101
  customDbUrl:
  isFulltext: true
  dateEnd: 99991231
  titleUrlDefault: https://road.issn.org
  omitProxy: true
  ssIdentifier: ssib058759023
  providerName: ISSN International Centre
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEI5KkRAXBALEsyoSPm5JHNvxcEu6qSrE41Kk3qpkN4HTIsFWqnpACCHKhYoDVMCFIxIV2gMn-kP4BWwf_4KZiTcJL_G4WN7x-POMxxvPJH543mWl88wGme4YXWQYoGR-B8Lc7yicrPp9nOCgoN3IN26axdvq2rJenjr0pbVqaXWYz_XWf7mv5H-sijS0K-2S_QfL1qBIwDzaF1O0MKZ_ZWORagELIolFqii16fXurQWiYohvDWesABBpJACLlUgtFcVYAWiNg5XEgzVBESVOBFiRGgFGxIwDyJNSdSwiiqU07jIFm-g6St0WslXVE6BMEorqcsuJ_-vahUpihAqoIgLGhvhtLGI9GQMMidoZ5rXcLGZIxobFsIYxo4BIonYJdFl4KxJUJGFNQ5H4bfw4FbYqIRHar0CqvZ48XFvtM1Ay0R9-kh51o4bnXffFitganrr7gO0WOhWxYlOEGcs4dQchctAAkhUjNoxpycOqJExJUDbNElqnHBZBygZGCecdBaHkJG-BK6YOisAtjxWJUBg--tXJCm72omMCVMhXQ9bTW2hbf2PVmqtcP1ZeT7WR_ef5FDTwhEr4cxP8NVoSGfnwwxnm7BUN19ZyLlV8CO9hSe_JaEntw7QdNqNT1N7P7UtovrZLukwNPavmt1FGy9pNDsmLhuaMJ40-MrqhNZ4OaKVX83VbY0wO7m4s9tAkBDLgW2brHjviXZroe-V32vK-vkGZDe60XNCl494xFzvOxtWD4IQ3tX73pHd1_G7n684m_fHHG0_Hz97svX2yv_Hh4NHj8c7Lg-3Xu1uj8YvNve3R_ujj3vvn-yPk2d7d-rz76dUpb2khXZpf7LgLUTo9HYUdlWcyzDFGkb7Mg1DlZRRIIyHqR1kpe7mGHh33mPUCv-j3dW5lLyhMqbSlIA975bQ3Pbg3KM54s34ooewXRW4yUCVYm-dQZqb0o15krIGz3oxTdcU97x6sfGfZc39iOO8dpXz1tvKCNz28v1pcRP99mM_wYPgGFw2rRw
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8ELDOF%E5%87%86%E5%88%99%E7%9A%84%E8%87%AA%E9%80%82%E5%BA%94%E9%AB%98%E6%96%AF%E5%90%8E%E7%AB%AF%E8%AF%AD%E7%A7%8D%E8%AF%86%E5%88%AB%E6%96%B9%E6%B3%95&rft.jtitle=%E9%80%9A%E4%BF%A1%E5%AD%A6%E6%8A%A5&rft.au=%E5%8F%B6%E4%B8%AD%E4%BB%98&rft.au=%E6%88%9A%E5%A9%B7&rft.au=%E6%9D%8E%E8%B5%9B%E5%B3%B0&rft.au=%E5%AE%8B%E5%BD%A6&rft.date=2017&rft.pub=%E4%B8%AD%E5%9B%BD%E7%A7%91%E5%AD%A6%E6%8A%80%E6%9C%AF%E5%A4%A7%E5%AD%A6%E8%AF%AD%E9%9F%B3%E5%8F%8A%E8%AF%AD%E8%A8%80%E4%BF%A1%E6%81%AF%E5%A4%84%E7%90%86%E5%9B%BD%E5%AE%B6%E5%B7%A5%E7%A8%8B%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E5%AE%89%E5%BE%BD%E5%90%88%E8%82%A5230027&rft.issn=1000-436X&rft.volume=38&rft.issue=4&rft.spage=17&rft.epage=24&rft_id=info:doi/10.11959%2Fj.issn.1000-436x.2017096&rft.externalDocID=txxb201704003
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Ftxxb%2Ftxxb.jpg