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
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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.