通信学报2017，Vol.38Issue(4)：17-24,8.DOI:10.11959/j.issn.1000-436x.2017096
基于LDOF准则的自适应高斯后端语种识别方法
Adaptive Gaussian back-end based on LDOF criterion for language recognition
摘要
Abstract
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.关键词
语种识别/类内多样性/自适应高斯后端/LDOFKey words
language recognition/inter-language variations/adaptive Gaussian back-end/LDOF分类
信息技术与安全科学引用本文复制引用
叶中付,戚婷,李赛峰,宋彦..基于LDOF准则的自适应高斯后端语种识别方法[J].通信学报,2017,38(4):17-24,8.基金项目
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 (No.2015A15) （No.2015A15）
