… We show the first successful use of Transformers in generating music that exhibits long-term …
Our work show that Transformers not only achieve state-of-the-art perplexity on modeling …

… and harmonic structure of music. With this approach, we build a Pop Music Transformer that
composes Pop piano music with better rhythmic structure than existing Transformer models. …

… for symbolic music generation [1,2], among which, the transformer model [3] has become
popular given its recent successes in piano music generation [4–7]. At the core of a transformer …

… With carefully examination of the music generated by our Theme Transformer, we found that
each occurrence of the conditioning theme (ie, a generated theme region) depends largely …

… established video-music rhythmic relationships, we propose a transformer-based approach
to generate background music for given videos, termed Controllable Music Transformer (CMT…

… In this paper, we propose SpecTNT, a Transformerbased … a novel variant of the
Transformer-inTransformer (TNT) … to music tagging, we clearly understand how chords of music …

… can see: 1) Music Transformer achieves a comparable PPL as other models on short music
… a model trained on short music sequences cannot well generalize to long music sequences. …

… a transformer-based model for generating a music transition to bridge two prepared music
clips. … from listeners, supporting that our generated transitions conform to background music. …

… we argue arise from the training objective; Music Transformer (Huang et al. 2018) occasion…
Consequently, music generated by such models can be distinguished from real music by a …

… to increasing the affordances of a Transformer-based system. To achieve this goal, we
develop a novel representation for multi-track musical material that accommodates a variety of …