基于区分性Model Pushing的语种识别方法
提出一种区分性Model Pushing方法，将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动，增大不同语种间的区分性，然后将移动后的支持向量反向应用于GMM。该方法既保留了SVM的区分性信息，又利用了GMM在短时语音上的优势，同时增加了目标与非目标的区分度。实验结果表明，区分性Model Pushing能有效地提高识别性能。...
Saved in:
| Published in | 电子技术应用 Vol. 38; no. 4; pp. 113 - 116 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
61906部队,江西鹰潭335000%国家数字交换系统工程技术研究中心,河南郑州,450002%61906部队,江西鹰潭,335000
2012
国家数字交换系统工程技术研究中心,河南郑州450002 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0258-7998 |
| DOI | 10.3969/j.issn.0258-7998.2012.04.034 |
Cover
| Abstract | 提出一种区分性Model Pushing方法，将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动，增大不同语种间的区分性，然后将移动后的支持向量反向应用于GMM。该方法既保留了SVM的区分性信息，又利用了GMM在短时语音上的优势，同时增加了目标与非目标的区分度。实验结果表明，区分性Model Pushing能有效地提高识别性能。 |
|---|---|
| AbstractList | 提出一种区分性Model Pushing方法，将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动，增大不同语种间的区分性，然后将移动后的支持向量反向应用于GMM。该方法既保留了SVM的区分性信息，又利用了GMM在短时语音上的优势，同时增加了目标与非目标的区分度。实验结果表明，区分性Model Pushing能有效地提高识别性能。 TN912.3; 提出一种区分性Model Pushing方法,将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动,增大不同语种间的区分性,然后将移动后的支持向量反向应用于GMM.该方法既保留了SVM的区分性信息,又利用了GMM在短时语音上的优势,同时增加了目标与非目标的区分度.实验结果表明,区分性Model Pushing能有效地提高识别性能. |
| Author | 刘伟伟 吉立新 李邵梅 徐文 |
| AuthorAffiliation | 国家数字交换系统工程技术研究中心,河南郑州450002 61906部队,江西鹰潭335000 |
| AuthorAffiliation_xml | – name: 国家数字交换系统工程技术研究中心,河南郑州450002;61906部队,江西鹰潭335000%国家数字交换系统工程技术研究中心,河南郑州,450002%61906部队,江西鹰潭,335000 |
| Author_FL | Xu Wen Liu Weiwei Li Shaomei Ji Lixin |
| Author_FL_xml | – sequence: 1 fullname: Liu Weiwei – sequence: 2 fullname: Ji Lixin – sequence: 3 fullname: Li Shaomei – sequence: 4 fullname: Xu Wen |
| Author_xml | – sequence: 1 fullname: 刘伟伟 吉立新 李邵梅 徐文 |
| BookMark | eNo9jz1LAzEcxjNUsNZ-BwXB6c4k_-SSjFLUChUduh-5XO96pea0oUidHKR0UDcdXBw7iHRwsp_Ha_sxPKk4PfDw43nZQhWb2w5CewT7oAJ10PMz56yPKZeeUEr6FBPqY-ZjYBVU_fc3Ud25LMKYEEwlhyoixdv8e_5UPMyLyXhxNz3L405_52LouplNl6_3q9nHcvq4mo2Lyfvi5Wvx-byNNhLdd536n9ZQ-_io3Wh6rfOT08ZhyzNcMk8IYEpoE0XAWZBQwWIVaS6liQOsQIJWOjA8AqEkxACK64AGnHNqsIyEgRraX8feaJtom4a9fDiwZWEY3_bcaPT7ELPyX0nurknTzW16Xe4OrwbZpR6MQkYYcCIY_ABucGFM |
| ClassificationCodes | TN912.3 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2RA 92L CQIGP W92 ~WA 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3969/j.issn.0258-7998.2012.04.034 |
| DatabaseName | 维普期刊资源整合服务平台 中文科技期刊数据库-CALIS站点 维普中文期刊数据库 中文科技期刊数据库-工程技术 中文科技期刊数据库- 镜像站点 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 |
| Discipline | Engineering |
| DocumentTitleAlternate | Language recognition based on discriminative Model Pushing |
| DocumentTitle_FL | Language recognition based on discriminative Model Pushing |
| EndPage | 116 |
| ExternalDocumentID | dzjsyy201204034 41435174 |
| GrantInformation_xml | – fundername: 国家863计划重点项目 funderid: (2011AA010603) |
| GroupedDBID | -0Y 2B. 2C0 2RA 5XA 5XJ 92H 92I 92L ACGFS ALMA_UNASSIGNED_HOLDINGS CCEZO CQIGP CUBFJ CW9 GROUPED_DOAJ TCJ TGT U1G U5S W92 ~WA 4A8 93N ABJNI PSX |
| ID | FETCH-LOGICAL-c584-773497acbb3546f274d9ba588cd609383a9a6c5b37983d3395a6265552c08b7c3 |
| ISSN | 0258-7998 |
| IngestDate | Thu May 29 04:04:52 EDT 2025 Wed Feb 14 10:47:13 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | 语种识别 高斯混合模型超矢量-支持向量机 超平面法向量 区分性Model Pushing |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c584-773497acbb3546f274d9ba588cd609383a9a6c5b37983d3395a6265552c08b7c3 |
| Notes | language recognition; discriminative Model Pushing; gaussian mixture model super vector-support vector machine; normal vector to hyperplanes To improve the performance of short utterances in this model, this work proposes discriminative Model Pushing that moves the support vectors in the direction of the normal to the separation hyperplanes trained by SVM. Then the moved support vectors are pushed back to GMM. By this means, the discriminative information of SVM and the advantage of GMM in short utter- ances recognition are retained, and the diversity between targets and nontargets is enhanced. Experimental results demonstrate that the proposed discriminative Model Pushing produce improvement over the baseline GMM-UBM, GSV-SVM and Model Pushing. Liu Weiwei, Ji Lixin, Li Shaomei, Xu Wen （1. National Digital Switching System Engineering＆Technological R＆D Center, Zhengzhou 450002, China; 2. Unit 61906, Yingtan 335000, China） 11-2305/TN |
| PageCount | 4 |
| ParticipantIDs | wanfang_journals_dzjsyy201204034 chongqing_primary_41435174 |
| PublicationCentury | 2000 |
| PublicationDate | 2012 |
| PublicationDateYYYYMMDD | 2012-01-01 |
| PublicationDate_xml | – year: 2012 text: 2012 |
| PublicationDecade | 2010 |
| PublicationTitle | 电子技术应用 |
| PublicationTitleAlternate | Application of Electronic Technique |
| PublicationTitle_FL | Application of Electronic Technique |
| PublicationYear | 2012 |
| Publisher | 61906部队,江西鹰潭335000%国家数字交换系统工程技术研究中心,河南郑州,450002%61906部队,江西鹰潭,335000 国家数字交换系统工程技术研究中心,河南郑州450002 |
| Publisher_xml | – name: 61906部队,江西鹰潭335000%国家数字交换系统工程技术研究中心,河南郑州,450002%61906部队,江西鹰潭,335000 – name: 国家数字交换系统工程技术研究中心,河南郑州450002 |
| SSID | ssib001102853 ssib017479494 ssib038074684 ssib051374551 ssj0042189 ssib023646353 |
| Score | 1.8654791 |
| Snippet | 提出一种区分性Model Pushing方法，将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动，增大不同语种间的区分性，然后将移动后的支持向量反向应用于GMM。该方法既保留了SVM的区分性信息，又利用了GMM在短时语音上的优势，同时增加了目标与非目标的区分度。实验结果表明，区分性Model... TN912.3; 提出一种区分性Model Pushing方法,将SVM训练出的支持向量沿最优分类面的法线方向进行适当移动,增大不同语种间的区分性,然后将移动后的支持向量反向应用于GMM.该方法既保留了SVM的区分性信息,又利用了GMM在短时语音上的优势,同时增加了目标与非目标的区分度.实验结果表明,区分性Model... |
| SourceID | wanfang chongqing |
| SourceType | Aggregation Database Publisher |
| StartPage | 113 |
| SubjectTerms | Pushing 区分性Model 语种识别 超平面法向量 高斯混合模型超矢量-支持向量机 |
| Title | 基于区分性Model Pushing的语种识别方法 |
| URI | http://lib.cqvip.com/qk/90393X/201204/41435174.html https://d.wanfangdata.com.cn/periodical/dzjsyy201204034 |
| Volume | 38 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR09bxMx1ApFQnRAfIqWD2Wop-rK3dk-2-NdclGFBFOQukW-u6QVQwo0HZqpA6o6ABsMLIipA0IdmMjvIWl_Bu_5nMuBUAUsJ8v3_N7zvRf7vRe_Z0LWhAHNGBjpmUJwj_fDgaclHhMrWGEYrH9ZgAnOT55Gm8_44y2x1Wh8rp1a2h9lG_n4j3kl_yNV6AO5YpbsP0i2Qgod0Ab5whMkDM-_kjFNBdUdmsQ05fhUKfaolu2BhqIqommEpxliibeeYZjOxpxoKqmGAZymisYdGrexJ5ZUtV0PjrQo4gRR6IgmGhsJo-V9lXOT1qIC8gLhAY_2LckYqeLAFmKDV8ATgJXAcXWA1hHRyk6hhdOZN9bt9HyqtOUtoarixF-3rbadsaYqtOQjGodUCTsuSR0jAO72WhfbCOqBzlAoT-ryhur5Ss1UTSN5bdkNynxWt4MHZfbm75sD05G2mwMS2KgI4PG-0Ja7dVHVX8tvczQowW27RC6HUgai5rVbixMNtIXFA4CwwC2WOCzPDyZd9R7L-_NokRosAia5ENWpJA4Wl_XY5txdIWuO9UcXMY6VQXZ2h9svQYNs-tlwYIbbNUupe51ccy5OMy719QZpjHdukuVa4ctbJJh-mvyYvJu-mUyPj2aHJ1Y3m043zz6-Pj_9enby9vz0aHr8Zfbh--zb-9uk20m7rU3PXd7h5WDTgtPGuJYmzzImeDQIJS90ZoRSeRH5milmtIlykTGpFSsY08KAay2ECHNfZTJnd8jScHfYv0ua-Oc1IALDV_W5jEyWaT_3-zkfCMUAeIWsVnPvvShrtPTmYlshTfcxeu6Hu9crxs_3Dg7w68E6xfjqRePvkasIWAbd7pOl0av9_gMwQ0fZQ6sIPwEfX2ND |
| linkProvider | Directory of Open Access Journals |
| 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%8E%E5%8C%BA%E5%88%86%E6%80%A7Model+Pushing%E7%9A%84%E8%AF%AD%E7%A7%8D%E8%AF%86%E5%88%AB%E6%96%B9%E6%B3%95&rft.jtitle=%E7%94%B5%E5%AD%90%E6%8A%80%E6%9C%AF%E5%BA%94%E7%94%A8&rft.au=%E5%88%98%E4%BC%9F%E4%BC%9F+%E5%90%89%E7%AB%8B%E6%96%B0+%E6%9D%8E%E9%82%B5%E6%A2%85+%E5%BE%90%E6%96%87&rft.date=2012&rft.issn=0258-7998&rft.volume=38&rft.issue=4&rft.spage=113&rft.epage=116&rft_id=info:doi/10.3969%2Fj.issn.0258-7998.2012.04.034&rft.externalDocID=41435174 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fimage.cqvip.com%2Fvip1000%2Fqk%2F90393X%2F90393X.jpg http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdzjsyy%2Fdzjsyy.jpg |