作者其他论文
文献详情
Approximate search of audio queries by using DTW with phone time boundary and data augmentation
文献类型:会议
作者:Xu, Haikua[1]  Hou, Jingyong[2]  Xiao, Xiong[3]  Pham, Van Tung[4]  Leung, Cheung-Chi[5]  Wang, Lei[6]  Do, Van Hai[7]  Lv, Hang[8]  Xie, Lei[9]  Ma, Bin[10]  Chng, Eng Siong[11]  Li, Haizhou[12]  
机构:[1]Temasek Laboratories, Nanyang Technological University, Singapore, Singapore
[2]School of Computer Science, Northwestern Polytechnical University(NWPU), Xi'an, China
[3]Temasek Laboratories, Nanyang Technological University, Singapore, Singapore
[4]School of Computer Engineering, Nanyang Technological University, Singapore, Singapore
[5]Institute for Infocomm Research(I2R), ASTAR, Singapore, Singapore
[6]Institute for Infocomm Research(I2R), ASTAR, Singapore, Singapore
[7]Temasek Laboratories, Nanyang Technological University, Singapore, Singapore
[8]School of Computer Science, Northwestern Polytechnical University(NWPU), Xi'an, China
[9]School of Computer Science, Northwestern Polytechnical University(NWPU), Xi'an, China
[10]Institute for Infocomm Research(I2R), ASTAR, Singapore, Singapore
[11]Temasek Laboratories, Nanyang Technological University, Singapore, Singapore |School of Computer Engineering, Nanyang Technological University, Singapore, Singapore
[12]Temasek Laboratories, Nanyang Technological University, Singapore, Singapore |School of Computer Engineering, Nanyang Technological University, Singapore, Singapore |Institute for Infocomm Research(I2R), ASTAR, Singapore, Singapore
年:2016
会议名称:41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
页码范围:6030-6034
会议地点:Shanghai, China
会议开始日期:2016-05-18
会议结束日期:2016-03-25
收录情况:EI(20162402489370)  
所属部门:计算机学院
人气指数:3030
浏览次数:2995
语言:外文
摘要:
Dynamic Time Warping (DTW) is widely used in language independent query-by-example (QbE) spoken term detection (STD) tasks due to its high performance. However, there are two limitations of DTW based template matching, 1) it is not straightforward to perform approximate match of audio queries; 2) DTW is sensitive to the mismatch of signal conditions between the query and the speech search data. To allow approximate search, we propose a partial template matching strategy using phone time boundary ...More
0
评论(0 条评论)
登录