Deep Sound Field Reconstruction in Real Rooms: Introducing the ISOBEL Sound Field Dataset
This work addresses the problem of efficient sound field acquisition for applications like personalized audio in reverberant rooms, but it is incremental as it builds on existing deep learning methods and focuses on low-frequency reconstruction.
The paper tackles sound field reconstruction in real rooms by introducing the ISOBEL dataset with measurements from four real rooms and advancing a deep learning method using a U-Net-like architecture to model magnitude and phase. The result is high-accuracy room transfer functions enabling personalized sound zones with contrast ratios comparable to ideal ones using 15 microphones below 150 Hz.
Knowledge of loudspeaker responses are useful in a number of applications, where a sound system is located inside a room that alters the listening experience depending on position within the room. Acquisition of sound fields for sound sources located in reverberant rooms can be achieved through labor intensive measurements of impulse response functions covering the room, or alternatively by means of reconstruction methods which can potentially require significantly fewer measurements. This paper extends evaluations of sound field reconstruction at low frequencies by introducing a dataset with measurements from four real rooms. The ISOBEL Sound Field dataset is publicly available, and aims to bridge the gap between synthetic and real-world sound fields in rectangular rooms. Moreover, the paper advances on a recent deep learning-based method for sound field reconstruction using a very low number of microphones, and proposes an approach for modeling both magnitude and phase response in a U-Net-like neural network architecture. The complex-valued sound field reconstruction demonstrates that the estimated room transfer functions are of high enough accuracy to allow for personalized sound zones with contrast ratios comparable to ideal room transfer functions using 15 microphones below 150 Hz.