The NNI query-by-example system for MediaEval 2015

Jingyong Hou; Van Tung Pham; Cheung Chi Leung; Lei Wang; Haihua Xu; Hang Lv; Lei Xie; Zhonghua Fu; Chongjia Ni; Xiong Xiao; Hongjie Chen; Shaofei Zhang; Sining Sun; Yougen Yuan; Pengcheng Li; Tin Lay Nwe; Sunil Sivadas; Bin Ma; Eng Siong Chng; Haizhou Li

The NNI query-by-example system for MediaEval 2015

Jingyong Hou, Van Tung Pham, Cheung Chi Leung, Lei Wang, Haihua Xu, Hang Lv, Lei Xie, Zhonghua Fu, Chongjia Ni, Xiong Xiao, Hongjie Chen, Shaofei Zhang, Sining Sun, Yougen Yuan, Pengcheng Li, Tin Lay Nwe, Sunil Sivadas, Bin Ma, Eng Siong Chng, Haizhou Li

计算机学院

科研成果: 期刊稿件 › 会议文章 › 同行评审

2 引用（Scopus）

摘要

This paper describes the system developed by the NNI team for the Query-by-Example Search on Speech Task (QUESST) in the MediaEval 2015 evaluation. Our submitted system mainly used bottleneck features/stacked bottleneck features (BNF/SBNF) trained from various resources. We investigated noise robustness techniques to deal with the noisy data of this year. The submitted system obtained the actual normalized cross entropy (actCnxe) of 0.761 and the actual Term Weighted Value (actTWV) of 0.270 on all types of queries of the evaluation data.

源语言	英语
期刊	CEUR Workshop Proceedings
卷	1436
出版状态	已出版 - 2015
活动	Multimedia Benchmark Workshop, MediaEval 2015 - Wurzen, 德国期限: 14 9月 2015 → 15 9月 2015

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{b60d07c0d2c043c5823ff57922461967,

title = "The NNI query-by-example system for MediaEval 2015",

abstract = "This paper describes the system developed by the NNI team for the Query-by-Example Search on Speech Task (QUESST) in the MediaEval 2015 evaluation. Our submitted system mainly used bottleneck features/stacked bottleneck features (BNF/SBNF) trained from various resources. We investigated noise robustness techniques to deal with the noisy data of this year. The submitted system obtained the actual normalized cross entropy (actCnxe) of 0.761 and the actual Term Weighted Value (actTWV) of 0.270 on all types of queries of the evaluation data.",

author = "Jingyong Hou and Pham, {Van Tung} and Leung, {Cheung Chi} and Lei Wang and Haihua Xu and Hang Lv and Lei Xie and Zhonghua Fu and Chongjia Ni and Xiong Xiao and Hongjie Chen and Shaofei Zhang and Sining Sun and Yougen Yuan and Pengcheng Li and Nwe, {Tin Lay} and Sunil Sivadas and Bin Ma and Chng, {Eng Siong} and Haizhou Li",

year = "2015",

language = "英语",

volume = "1436",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

note = "Multimedia Benchmark Workshop, MediaEval 2015 ; Conference date: 14-09-2015 Through 15-09-2015",

}

TY - JOUR

T1 - The NNI query-by-example system for MediaEval 2015

AU - Hou, Jingyong

AU - Pham, Van Tung

AU - Leung, Cheung Chi

AU - Wang, Lei

AU - Xu, Haihua

AU - Lv, Hang

AU - Xie, Lei

AU - Fu, Zhonghua

AU - Ni, Chongjia

AU - Xiao, Xiong

AU - Chen, Hongjie

AU - Zhang, Shaofei

AU - Sun, Sining

AU - Yuan, Yougen

AU - Li, Pengcheng

AU - Nwe, Tin Lay

AU - Sivadas, Sunil

AU - Ma, Bin

AU - Chng, Eng Siong

AU - Li, Haizhou

PY - 2015

Y1 - 2015

N2 - This paper describes the system developed by the NNI team for the Query-by-Example Search on Speech Task (QUESST) in the MediaEval 2015 evaluation. Our submitted system mainly used bottleneck features/stacked bottleneck features (BNF/SBNF) trained from various resources. We investigated noise robustness techniques to deal with the noisy data of this year. The submitted system obtained the actual normalized cross entropy (actCnxe) of 0.761 and the actual Term Weighted Value (actTWV) of 0.270 on all types of queries of the evaluation data.

AB - This paper describes the system developed by the NNI team for the Query-by-Example Search on Speech Task (QUESST) in the MediaEval 2015 evaluation. Our submitted system mainly used bottleneck features/stacked bottleneck features (BNF/SBNF) trained from various resources. We investigated noise robustness techniques to deal with the noisy data of this year. The submitted system obtained the actual normalized cross entropy (actCnxe) of 0.761 and the actual Term Weighted Value (actTWV) of 0.270 on all types of queries of the evaluation data.

UR - http://www.scopus.com/inward/record.url?scp=84989856888&partnerID=8YFLogxK

M3 - 会议文章

AN - SCOPUS:84989856888

SN - 1613-0073

VL - 1436

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

T2 - Multimedia Benchmark Workshop, MediaEval 2015

Y2 - 14 September 2015 through 15 September 2015

ER -