Chord recognition systems use temporal models to post-process frame-wise chord predictions from acoustic models. Traditionally, first-order models such as Hidden Markov Models were used for this task, with recent works suggesting to apply Recurrent Neural Networks instead. In this paper, we argue that learning complex temporal models at the level of audio frames is futile on principle, and that non-Markovian models do not perform better than their first-order counterparts. We support our argument through experiments on the McGill Billboard dataset. We show that when learning complex temporal models at the frame level, improvements in chord sequence modelling are marginal and that these improvements do not translate when applied within a full chord recognition system.
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
