applied sciences Article Designing Audio Equalization Filters by Deep Neural Networks Giovanni Pepe 1, Leonardo Gabrielli 1,* , Stefano Squartini 1 and Luca Cattani 2 1 Department of Information Engineering, Università Politecnica delle Marche, 60131 Ancona, Italy;
[email protected] (G.P.);
[email protected] (S.S.) 2 ASK Industries SpA, 42124 Reggio Emilia, Italy;
[email protected] * Correspondence:
[email protected] Received: 26 February 2020; Accepted: 31 March 2020; Published: 4 April 2020 Abstract: Audio equalization is an active research topic aiming at improving the audio quality of a loudspeaker system by correcting the overall frequency response using linear filters. The estimation of their coefficients is not an easy task, especially in binaural and multipoint scenarios, due to the contribution of multiple impulse responses to each listening point. This paper presents a deep learning approach for tuning filter coefficients employing three different neural networks architectures—the Multilayer Perceptron, the Convolutional Neural Network, and the Convolutional Autoencoder. Suitable loss functions are proposed for each architecture, and are formulated in terms of spectral Euclidean distance. The experiments were conducted in the automotive scenario, considering several loudspeakers and microphones. The obtained results show that deep learning techniques give superior performance compared to baseline methods, achieving almost flat magnitude frequency response. Keywords: deep neural networks; FIR filter design; audio equalization; automotive audio 1. Introduction Listening environments are characterized by reflections and reverberations that can adversely affect listening [1] and attention [2], adding unwanted artifacts to the sound produced by an acoustic source. For this reason, audio equalization is needed in order to improve sound quality reproduction.