← Back to all news
arXiv Machine Learning By Song-Ze Yu, Fang-Duo Tsai, Yi-Hsuan Yang

MIDI-REPA: Improving Text-to-Music Generation with Symbolic Representation Alignment

Read the original on arXiv Machine Learning →

MIDI-REPA is a framework that aligns symbolic music representations with intermediate layers of a flow-matching DiT model to improve text-to-music generation. By deriving MIDI supervision from automatic music transcription and aligning a MuScriptor-derived piano roll with an early DiT layer throughout the flow trajectory, the method achieves competitive performance on the ATTM objective metrics without extra training data or techniques. The approach is trainable on a single RTX 3090 in about 31 hours and is supported by released transcription pipeline, training code, and audio samples.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
2d ago

Gangqinpu: A Multi-Genre, Multi-Task Piano Dataset with Aligned Audio, MIDI, and Musical Scores

Gangqinpu is a large, multi‑genre piano dataset that provides aligned audio, MIDI, and musical scores for 18,786 pieces, covering pop, classical, jazz, folk/traditional, rock, and blues. The dataset includes automatic note‑level alignments, beat/downbeat annotations, genre labels, and a binary classifier to filter non‑expressive performances. It is designed to reduce data leakage with ASAP splits and has shown cross‑dataset improvements in beat tracking and in‑domain gains for transcription and expressive performance rendering.

By Wei Zeng, Anvay Mathur, Ye Wang
More like this →
arXiv AI
Jun 26

Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training

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.

By Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li
llmsefficiencybenchmarks
More like this →
arXiv Machine Learning
6d ago

Piano2Pop: Expanding Piano Demos into Pop Productions Without Aligned Supervision

Piano2Pop is a music‑expansion task that converts piano MIDI into full instrumental pop productions. The method uses a pseudo‑supervised approach that conditions a pretrained flow‑matching model on piano rolls, trained on synthetic piano‑instrumental pairs derived from pop recordings. Experiments on 476 real‑world piano‑cover/pop pairs show that a pair‑supervised piano‑cover generator outperforms zero‑shot baselines, while function‑selective transcription (FST) reduces piano‑heavy outputs in pair‑free training and remains a promising alternative.

By Yun-Chen Cheng, Chih-Pin Tan, Tzu-Hung Huang, Yi-Hsuan Yang
fine-tuning
More like this →