针对实际应用中移动说话人场景,相邻语音帧之间的空间相关性急剧下降会导致声源定位估计性能下降的问题,提出利用语音频点间的空间相关性进行频域联合稀疏估计,从而提高声源移动条件下的声源定位性能.实验结果表明,频域联合稀疏的波达方...针对实际应用中移动说话人场景,相邻语音帧之间的空间相关性急剧下降会导致声源定位估计性能下降的问题,提出利用语音频点间的空间相关性进行频域联合稀疏估计,从而提高声源移动条件下的声源定位性能.实验结果表明,频域联合稀疏的波达方向(direction of arrival,DOA)估计算法在移动说话人场景中,性能优于传统定位算法和基于压缩感知(compressed sensing,CS)的正交匹配追踪算法.展开更多
本文研究了一种基于双层搜索空间聚类(Two-Level Search Space Clustering,TL-SSC)的移动声源定位与跟踪方法,采用TL-SSC方法和平均值计算方法来确定移动声源在离散时间域上的坐标,并且在声源短暂停止发声时能够通过速度与加速度计算进...本文研究了一种基于双层搜索空间聚类(Two-Level Search Space Clustering,TL-SSC)的移动声源定位与跟踪方法,采用TL-SSC方法和平均值计算方法来确定移动声源在离散时间域上的坐标,并且在声源短暂停止发声时能够通过速度与加速度计算进行位置跟踪。仿真实验结果证实了该方法在不同混响环境下能够保持定位的准确性,满足移动声源实时定位的需求。展开更多
To solve the problem of multiple moving sources passive location, a novel blind source separa- tion （BSS） algorithm based on the muhiset canonical correlation analysis （MCCA） is presented by exploiting the differe...To solve the problem of multiple moving sources passive location, a novel blind source separa- tion （BSS） algorithm based on the muhiset canonical correlation analysis （MCCA） is presented by exploiting the different temporal structure of uncorrelated source signals first, and then on the basis of this algorithm, a novel multiple moving sources passive location method is proposed using time difference of arrival （TDOA） and frequency difference of arrival （FDOA） measurements. The key technique of this location method is TDOA and FDOA joint estimation, which is based on BSS. By blindly separating mixed signals from multiple moving sources, the multiple sources location problem can be translated to each source location in turn, and the effect of interference and noise can also he removed. The simulation results illustrate that the performance of the MCCA algorithm is very good with relatively light computation burden, and the location algorithm is relatively simple and effective.展开更多
文摘针对实际应用中移动说话人场景,相邻语音帧之间的空间相关性急剧下降会导致声源定位估计性能下降的问题,提出利用语音频点间的空间相关性进行频域联合稀疏估计,从而提高声源移动条件下的声源定位性能.实验结果表明,频域联合稀疏的波达方向(direction of arrival,DOA)估计算法在移动说话人场景中,性能优于传统定位算法和基于压缩感知(compressed sensing,CS)的正交匹配追踪算法.
文摘本文研究了一种基于双层搜索空间聚类(Two-Level Search Space Clustering,TL-SSC)的移动声源定位与跟踪方法,采用TL-SSC方法和平均值计算方法来确定移动声源在离散时间域上的坐标,并且在声源短暂停止发声时能够通过速度与加速度计算进行位置跟踪。仿真实验结果证实了该方法在不同混响环境下能够保持定位的准确性,满足移动声源实时定位的需求。
基金Supported by the National High Technology Research and Development Program of China(No.2009AAJ116,2009AAJ208,2010AA7010422)the National Science Foundation for Post-Doctoral Scientists of China(No.20080431379,200902671)the Hubei Natural Science Foundation(No.2009CDB031)
文摘To solve the problem of multiple moving sources passive location, a novel blind source separa- tion （BSS） algorithm based on the muhiset canonical correlation analysis （MCCA） is presented by exploiting the different temporal structure of uncorrelated source signals first, and then on the basis of this algorithm, a novel multiple moving sources passive location method is proposed using time difference of arrival （TDOA） and frequency difference of arrival （FDOA） measurements. The key technique of this location method is TDOA and FDOA joint estimation, which is based on BSS. By blindly separating mixed signals from multiple moving sources, the multiple sources location problem can be translated to each source location in turn, and the effect of interference and noise can also he removed. The simulation results illustrate that the performance of the MCCA algorithm is very good with relatively light computation burden, and the location algorithm is relatively simple and effective.
