Superiorities of the proposed method are to incorporate acoustic characteristics of a targeted environment and even remaining uncertainty of TDOA estimations into the learning model before conducting its prediction and to be applicable for both synchronous or asynchronous distributed microphone sensor networks.
As the delay time decreases, it is as if the (virtual) reflecting wall were moving toward you.
For a new acoustic source, if its sound signals are recorded, the correspondingly computed TDOAs can be fed into the learned model to predict the location of the new source. A delayed signal emulates a reflection of the sound wave. Then, given a set of pre-recorded sound measurements and their corresponding source locations, the multilevel B-Splines based learning model is proposed to be trained by the input of the known TDOAs and the output of the known coordinates of the sound source locations. It is first to propose a new concept in which coordinates of a sound source location are defined as functions of TDOAs, computing for each pair of microphone signals in the network. Such time delays will be called feasible and the derived necessary and. In this paper, a new learning approach for sound source localization is presented using ad hoc either synchronous or asynchronous distributed microphone networks based on time differences of arrival (TDOA) estimation. Sound source localization (SSL) in a robotic platform has been essential in the.
0 kommentar(er)
