Multilevel B-Splines-Based Learning Approach for Sound Source Localization

Free-Field TDOA-AOA Sound Source Localization Using Three Soundfield Microphones

“…In this section, we explain the proposed approach for estimating TDOA and AOA values, computed from the real sound measurements collected by three soundfield microphone stations. Given that the solution (17) performs minimization of the sum of squared residuals with respect to measurement error, it was essential to determine observation uncertainties σ RD and σ AOA of the proposed TDOA-AOA estimation method in free field conditions. In this work, to ensure universal reference regarding methods uncertainties, all measurements are made in a small anechoic chamber [56] which facilitates free-field conditions where no reverberation of the sound source is present.…”

“…For instance, in [49] authors employed deep model for SSL, where it was shown that deep learning-based system achieved higher accuracy under low SNR conditions in comparison with cross-correlation phase transform (GCC-PHAT) method. Authors in [17] proposed a novel learning approach for SSL based on TDOA estimation, where coordinates of a sound source were defined as functions of TDOA. In their work, pre-recorded sound measurements and their corresponding source locations were used to train the multilevel B-Splines based learning model.…”

“…where (17) assumes that the measurement vector is corrupted with small Gaussian noise defined by covariance matrix Q, pointing to the need of investigating the uncertainty of our TDOA estimation method. In order to analyze our TDOA based estimation performance given measurement duration t, we examined uncertainty reduction when the length of the sound signal used for estimation increases.…”

“…In contrast, the indirect approach is based on using estimated TDOAs measurements, where the sound source is ascertained by addressing criteria such as the hypercone fitting problem [16]. Although results obtained by the indirect method are more prone to error as they are more sensitive to background noise, and reflections oppose to direct methods, the main advantage of indirect TDOA based approach is that it can be effectively used in distributed microphone network since it only requires for TDOA values to be transmitted and not raw sound signal data [17].…”

Can a Robot Hear the Shape and Dimensions of a Room?

“…Room geometry including shape and wall locations or dimension of a room plays a very crucial role in many applications. For instance, geometrical characteristics of a room can ameliorate accuracy of results for applications such as indoor sound source localization [1], [2], sound field reproduction [3] and mapping a 3D sound source in autonomous robotic systems [4]. Likewise, in other applications including teleconferencing, virtual reality and auralization, geometrical information of a room can be exploited to create a hallucination or counterbalance effect of room reverberations [5].…”