Adaptive Gaussian back-end based on LDOF criterion for language recognition
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 m...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2017-04-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017096/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539485191372800 |
|---|---|
| author | Zhong-fu YE Ting QI Sai-feng LI Yan SONG |
| author_facet | Zhong-fu YE Ting QI Sai-feng LI Yan SONG |
| author_sort | Zhong-fu YE |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-239297f6344f4c0aab696e302db9c398 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2017-04-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-239297f6344f4c0aab696e302db9c3982025-01-14T07:11:58ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2017-04-0138172459708925Adaptive Gaussian back-end based on LDOF criterion for language recognitionZhong-fu YETing QISai-feng LIYan SONGIn 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.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017096/language recognitioninter-language variationsadaptive Gaussian back-endLDOF |
| spellingShingle | Zhong-fu YE Ting QI Sai-feng LI Yan SONG Adaptive Gaussian back-end based on LDOF criterion for language recognition Tongxin xuebao language recognition inter-language variations adaptive Gaussian back-end LDOF |
| title | Adaptive Gaussian back-end based on LDOF criterion for language recognition |
| title_full | Adaptive Gaussian back-end based on LDOF criterion for language recognition |
| title_fullStr | Adaptive Gaussian back-end based on LDOF criterion for language recognition |
| title_full_unstemmed | Adaptive Gaussian back-end based on LDOF criterion for language recognition |
| title_short | Adaptive Gaussian back-end based on LDOF criterion for language recognition |
| title_sort | adaptive gaussian back end based on ldof criterion for language recognition |
| topic | language recognition inter-language variations adaptive Gaussian back-end LDOF |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2017096/ |
| work_keys_str_mv | AT zhongfuye adaptivegaussianbackendbasedonldofcriterionforlanguagerecognition AT tingqi adaptivegaussianbackendbasedonldofcriterionforlanguagerecognition AT saifengli adaptivegaussianbackendbasedonldofcriterionforlanguagerecognition AT yansong adaptivegaussianbackendbasedonldofcriterionforlanguagerecognition |