点击次数：

DOI码：10.1109/ICMEW.2014.6890706

发表刊物：2014 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (ICMEW)

刊物所在地：UNITED STATES

关键字：speech/music discrimination, decision treefusion

摘要：Aimed at the problem of real-time speech and music discrimination, this paper proposes a frame-level classification method by using a novel "butterfly-like" fusion strategy based on decision tree (D-Tree). In our method, some homotypes of long-term features but in different time lengths are extracted to train each subclassifier and make the fusion resultful. A testing experiment indicates our approach can achieve the desirable performance in reducing the misclassification and the imbalance of decision tree model. Meanwhile, superiorities in low overheads of computational complexity and memory resource make it competitive in practical applications.

合写作者：Weibei Dou,杨华中

第一作者：Min Lu,Shuhua Zhang

论文类型：会议论文

通讯作者：Weibei Dou,Shuhua Zhang,Shuhua Zhang

ISSN号：1945-7871

是否译文：否

发表时间：2014-07-14