搜索资源列表
-
2下载:
一种新的基于麦克风阵列的近场声源定位和语音分离算法,它结合双波束二维定位和近场最小方差波束形成技术在阵列近场范围内实现声源定位和语音分离。-based on a microphone array of near-field acoustic source localization and speech separation algorithm, It combines two-beam two-dimensional positioning and near-field minimum vari
-
-
0下载:
采用滤波器组,将盲分离与声源定位结合在一起。滤波器组中分别进行子带处理,并且在每个子带中进行声源定位,最后综合所有子带估计的方向得到多个声源的方位信息,同时将声源信息作为ICA分析的约束条件,可以在色噪声及多得到更好的盲分离效果。其优势在于用滤波器组进行多次的估计声源方向,再加以合适的权值均衡后即可得到更优的估计。-The use of filters will be blind source separation and sound localization together. Filter
-
-
0下载:
结合马尔可夫过程,提出一种概率论的声源定位算法,并给出了基于DSP的机器人实现。其中声源定位部分采用三个麦克风呈三角形放置,为减小由于噪声等引起的TDOA估计误差,采用马尔可夫过程计算时延,这样计算的时延会更可靠。该方案中的声源定位也属于一维定位,即只需知道声源的方向角-Combination of Markov process, a probability theory of sound source location algorithm, and give the robot based o
-
-
0下载:
In this paper, we investigate the problem of
reliable detection and localization of active sound source
using a new fusion approach of the vision and the
acoustic data that enables reducing errors of acoustic
localization caused mainly by syn
-