Companion page for the paper submitted to the 27th International Conference on Audio Effcts (DAFx24), Guilford, UK, 3-7 September 2024 .
Abstract: Active Acoustics (AA) refers to an electroacoustic system that actively modifies the acoustics of a room. For common use cases, the number of transducers---loudspeakers and microphones---involved in the system is high, resulting in a large number of system parameters. To optimally blend the response of the system into the natural acoustics of the room, the parameters require careful tuning, which is a time-consuming process performed by an expert. In this paper, we present a differentiable AA framework, which allows multi-objective optimization without impairing architecture flexibility. The system is implemented in PyTorch so that it can be easily translated into a machine-learning pipeline, thus automating the tuning process. The objective of the pipeline is to optimize the digital signal processor (DSP) component to obtain a colorless feedback loop. We investigate the effectiveness of DSPs composed of finite impulse response filters, which are unconstrained during the optimization. We study multiple filter orders, number of transducers, and loss functions. Different loss functions behave similarly with low filter order and low number of transducers. Increasing the number of transducers and the order of the filters improves results and accentuates the difference in the performance of the loss functions.
