Bass Enhancement Settings in Portable Devices Based on Music Genre Recognition

Abstract

The paper presents a novel approach to the Virtual Bass Synthesis (VBS) applied to mobile devices, called Smart VBS (SVBS). The proposed algorithm uses an intelligent, rule-based settingofbasssynthesisparametersadjustedtotheparticularmusicgenre.Harmonicgeneration is based on a nonlinear device (NLD) method with the intelligent controlling system adapting to the recognized music genre. To automatically classify music genres, the k-Nearest Neighbor classifier combined with the Principal Component Analysis (PCA) method is employed. To fine tune the SVBS algorithm, the MUSHRA test is performed. Subjects are presented with music excerpts belonging to various genres, unprocessed and also processed by SVBS and a conventional bass boost algorithm. Listening tests show that subjects in most cases prefer the SVBS strategy developed by the authors in favor of both the conventional bass boost algorithm and the unprocessed audio file. Furthermore, the listeners indicated that perception of the SVBS-processed music excerpts is similar for several types of portable devices.