Dimos Makris

TL;DR: Results on drums�’ rhythm sequences are presented indicating that the CNSL architecture is effective in producing drums’ sequences that resemble a learnt style, while at the same time conform to given constraints.

TL;DR: The Greek Music Dataset (GMD), a collection of musical information pertaining to Greek musical pieces, is presented, a significant extension of the Greek Audio Datasets by addition of symbolic information, both features and raw MIDI files, and inclusion of multi-label manual genre categorisation.

TL;DR: In this paper , a sequence-to-sequence architecture was proposed for conditional drums generation using a novel data encoding scheme inspired by the Compound Word representation, a tokenization process of sequential data, where a bidirectional long short-term memory (BiLSTM) encoder receives information about the conditioning parameters (i.e., accompanying tracks and musical attributes), while a Transformer-based Decoder with relative global attention produces the generated drum sequences.

TL;DR: The experimental results demonstrate that the proposed BVL method indeed efficiently captures (in a statistical sense) the characteristic BVL features of the examined musical idioms.