中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Real-time acoustic source separation based on Kalman filter

文献类型:会议论文

作者Wei YJ(魏阳杰); Wang Y(王义); He YQ(何玉庆)
出版日期2015
会议名称2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA)
会议日期June 15-17, 2015
会议地点Auckland, New Zealand
关键词Blind source separation (BSS) Kalman filter direction prediction component
页码1273-1278
中文摘要Deterministic techniques are based on the source-directions and multipath characteristics of the reverberant environment for different source signals. However, searching for the desired directions of the time-block sequence of an acoustic signal is time consuming, and existing deterministic methods rarely consider the motion properties of the acoustic source. In this paper, a real-time acoustic source separation based on a Kalman filter is proposed. First, the convolutive mixture signals captured by the coincident array geometry are formulated, and the basic principles of acoustic source separation based on intensity vector statistics are introduced. Then, a dynamic source-direction prediction method for real-time blind source separation based on a Kalman filter is proposed to predict the directions of a time sequential signal. Finally, extensive experiments are performed with three-source convolutive mixtures of speech in English and Chinese, whose direction varies in linear and nonlinear motions. The signal-to-distortion and signal-to-interference of the separated signals are calculated, and the experimental results demonstrate the feasibility and validity of the proposed method.
收录类别EI ; CPCI(ISTP)
产权排序2
会议录Proceedings of the 2015 10th IEEE Conference on Industrial Electronics and Applications, ICIEA 2015
会议录出版者IEEE
会议录出版地Piscataway, NJ, USA
语种英语
ISBN号978-1-4673-7317-3
WOS记录号WOS:000377208900231
源URL[http://ir.sia.cn/handle/173321/17737]  
专题沈阳自动化研究所_机器人学研究室
推荐引用方式
GB/T 7714
Wei YJ,Wang Y,He YQ. Real-time acoustic source separation based on Kalman filter[C]. 见:2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA). Auckland, New Zealand. June 15-17, 2015.

入库方式: OAI收割

来源:沈阳自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。