We study generative modeling of Bach-style symbolic piano music using a shared MIDI corpus and three model families: autoregressive LSTMs with attention, latent-variable models including recurrent VAEs and vector-quantized VAEs, and generative adversarial networks. We compare their ability to model polyphonic note sequences, learn useful latent representations, and generate stylistically coherent compositions.
arXiv:2606. 13626v2 Announce Type: replace-cross Abstract: We study generative modeling of Bach-style symbolic piano music using a shared MIDI corpus and three model families: autoregressive LSTMs with attention, latent-variable models including recurrent VAEs and vector-quantized VAEs, and generative adversarial networks.
arXiv:2608. 03050v1 Announce Type: cross Abstract: What is music style?
The paper introduces Musical Attention, a Transformer-based music generation model that incorporates meta-information such as bar numbers, key, signatures, and tempos into its attention mechanism. By representing each note with five events (pitch, bar number, onset, duration, velocity) plus three metadata elements, the model captures correlations among eight features, improving musical coherence and reducing repetition. Experiments show that Musical Attention outperforms prior methods like Full Attention and Strided Attention in coherence, variation, and overall quality, producing more diverse and harmonically consistent melodies.
arXiv:2607. 14537v1 Announce Type: cross Abstract: Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures.
arXiv:2506. 14293v4 Announce Type: replace-cross Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song.
The paper introduces CPR, a piano rendering framework that combines continuous autoregressive modeling with local flow matching and full‑sequence refinement. It predicts continuous hidden states, generates 24 kHz acoustic latents, and upsamples to 48 kHz, while new techniques BREPA and MT‑RoPE enhance musical semantics and cross‑modal alignment.
arXiv:2607. 27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes.
The paper introduces a lightweight technique to steer the pitch content of audio generated by the Stable Audio Open diffusion model. A small convolutional probe (~125k parameters) is trained to decode frame‑level pitch‑class activations from the model’s latent space using paired audio and MIDI data. During inference, the frozen probe acts as a differentiable loss, guiding generation toward a user‑specified pitch‑class sequence without retraining the base model, and improves melodic coherence by 2.4× over the unguided baseline.
The paper introduces Whole-Piece Training for Symbolic Music Language Models using Full-Horizon Compressed Recurrence (FHCR), which maintains the full temporal horizon of recurrent memory while compressing its key-value representation to fit GPU limits. An evaluation diagnostic, KV-Reset Context Utilization (KRCU), demonstrates that full-horizon models retain long-range context beyond local windows, whereas limiting recurrent memory weakens this dependence. FHCR thus preserves long-range context utilization while significantly reducing recurrent memory cost, enabling efficient whole-piece modeling.
Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes. However, these methods often disregard dependencies between notes, which poses a potential limitation in assessing the similarity between two sets of performances.
arXiv:2512. 02652v2 Announce Type: replace-cross Abstract: Existing methods for expressive music performance rendering, a conditional generation task that aims to generate a human-like performance from a symbolic score, rely on supervised learning over small labeled datasets, which limits scaling of both data volume and model size, despite the availability of vast unlabeled music, as in vision and language.
The paper introduces a supervised end-to-end benchmark for restoring orchestral historical music, addressing the lack of ground-truth pairs in early‑20th‑century recordings. It simulates the historical degradation process more accurately than prior work and trains a latent flow‑matching model that surpasses existing HMR baselines in various evaluations. Additionally, the authors release a 9.3‑hour license‑free test set, code, and audio demos for the community.