Inferring Room Geometries

Abstract

Determining the geometry of an acoustic enclosure using microphone arrays has become an active area of research. Knowledge gained about the acoustic environment, such as the location of reflectors, can be advantageous for applications such as sound source localization, dereverberation and adaptive echo cancellation by assisting in tracking environment changes and helping the initialization of such algorithms. A methodology to blindly infer the geometry of an acoustic enclosure by estimating the location of reflective surfaces based on acoustic measurements using an arbitrary array geometry is developed and analyzed. The starting point of this work considers a geometric constraint, valid both in two and three-dimensions, that converts time-of-arrival and time-difference-pf-arrival information into elliptical constraints about the location of reflectors. Multiple constraints are combined to yield the line or plane parameters of the reflectors by minimizing a specific cost function in the least-squares sense. An iterative constrained least-squares estimator, along with a closed-form estimator, that performs optimally in a noise-free scenario, solve the associated common tangent estimation problem that arises from the geometric constraint. Additionally, a Hough transform based data fusion and estimation technique, that considers acquisitions from multiple source positions, refines the reflector localization even in adverse conditions. An extension to the geometric inference framework, that includes the estimation of the actual speed of sound to improve the accuracy under temperature variations, is presented that also reduces the required prior information needed such that only relative microphone positions in the array are required for the localization of acoustic reflectors. Simulated and real-world experiments demonstrate the feasibility of the proposed method.