Towards Playlist Generation Algorithms Using RNNs Trained on Within-Track Transitions
This addresses playlist creation for music listeners, but it appears incremental as it builds on existing methods with qualitative results.
The paper tackled playlist generation by modeling transitions between tracks using a recurrent neural network trained on within-track transitions, with qualitative observations showing effective modeling of music track transitions.
We introduce a novel playlist generation algorithm that focuses on the quality of transitions using a recurrent neural network (RNN). The proposed model assumes that optimal transitions between tracks can be modelled and predicted by internal transitions within music tracks. We introduce modelling sequences of high-level music descriptors using RNNs and discuss an experiment involving different similarity functions, where the sequences are provided by a musical structural analysis algorithm. Qualitative observations show that the proposed approach can effectively model transitions of music tracks in playlists.