TUTTI is a new pre‑training framework for audio‑to‑score transcription that uses a large, fully synthetic multi‑instrument dataset generated by a symbolic music model. The approach trains a standard Transformer encoder‑decoder on these synthetic audio‑score pairs, producing a stronger foundational representation than single‑instrument training. When fine‑tuned on real datasets, TUTTI surpasses prior methods, achieving state‑of‑the‑art results and demonstrating strong cross‑instrument transferability.
By Jianhuai Hu, Yashan Wang, Shangda Wu, Zhancheng Guo, Shijie Liang, Wuna Meng, Chuanqi Yang, Xiaobing Li, Feng Yu, Maosong Sun
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
arXiv:2608. 06165v1 Announce Type: cross Abstract: Existing audio-to-score (A2S) systems primarily focus on classical music, and the application to popular music remains underexplored.
By Eoin Cummins, Zhongyi Huang, Alexandre D'Hooge, Zhuoro Mo, Yaolong Ju
arXiv:2606. 07387v1 Announce Type: new Abstract: State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages.
By Yun-Chen Cheng, Tzu-Hung Huang, Chih-Pin Tan
DuET is a Dual-Encoder Transformer that jointly learns note-level piano performance-to-score transcription and frame-level beat/downbeat tracking. It uses bidirectional cross‑attention between note and frame encoders and an autoregressive decoder that alternates between their representations to predict structured score attributes. The model introduces TimeRoPE and Time‑Pitch Rotary Positional Encoding (TPRoPE) to share a performance‑time reference and encode relative temporal and pitch relationships, achieving significant error reductions on ASAP and Gangqinpu datasets.
By Wei Zeng, Ye Wang
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.
By Song-Ze Yu, Fang-Duo Tsai, Yi-Hsuan Yang
arXiv:2502. 16584v2 Announce Type: replace-cross Abstract: Recent advancements in audio tokenization have significantly enhanced the integration of audio capabilities into large language models (LLMs).
By Liumeng Xue, Ziya Zhou, Jiahao Pan, Zixuan Li, Shuai Fan, Yinghao Ma, Sitong Cheng, Dongchao Yang, Haohan Guo, Yujia Xiao, Xinsheng Wang, Zixuan Shen, Chuanbo Zhu, Xinshen Zhang, Tianchi Liu, Ruibin Yuan, Zeyue Tian, Haohe Liu, Xingjian Du, Emmanouil Benetos, Ge Zhang, Yike Guo, Wei Xue
arXiv:2607. 08168v1 Announce Type: cross Abstract: Existing methods for automatic music transcription are often limited to single-instrument recordings or fail on complex, real music mixes.
By Simon Rouard, Michael Krause, Axel Roebel, Carl-Johann Simon-Gabriel, Alexandre D\'efossez
MuQ-Eval is an open‑source per‑sample quality metric for AI‑generated music that uses frozen MuQ‑310M features and a lightweight prediction head trained on the MusicEval dataset. The simplest model—attention‑pooled frozen features plus a two‑layer MLP—achieves high correlation with human judgments (system‑level SRCC = 0.957, utterance‑level SRCC = 0.838). The metric is real‑time on a single consumer GPU, outperforms existing open per‑sample metrics, and supports personalized evaluators via LoRA adaptation on as few as 150 clips.
By Di Zhu, Zihan Chen, Zixuan Li
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
Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM.
DuoTok is a source‑aware dual‑track music tokenizer designed for vocal‑accompaniment generation. It first learns a semantic audio representation via self‑supervised pretraining, then refines source‑aware structure with feature‑replacement noise and multi‑task supervision (spectral reconstruction, source separation regularization, and an ASR head for lyric alignment). The encoder is frozen and hard‑routed codebooks for vocals and accompaniment are learned, while a diffusion decoder restores fine acoustic detail from the discrete tokens, achieving a favorable predictability‑fidelity trade‑off at ultra‑low bitrate across public benchmarks.
By Rui Lin, Zhiyue Wu, Jiahe Lei, Kangdi Wang, Weixiong Chen, Junyu Dai, Tao Jiang