ONOTE is a unified framework that treats music as a scientifically structured domain of measurable cross-representation correspondences, focusing on omnimodal notation processing centered on sheet music. It introduces a test-only benchmark drawing from diverse musical sources—including staff, Jianpu, and tablature—across varied genres, instruments, and structural conditions, with aligned multimodal derivatives. The framework supports four complementary tasks—score understanding, notation conversion, audio transcription, and symbolic generation—while constructing a provenance-bearing proposition hypergraph from external music-theory materials for evidence retrieval and deterministic validity checks.
arXiv:2607. 05902v1 Announce Type: cross Abstract: Chamber music, as a highly precise multi-part interactive system, contains a logic of "role assignment and dynamic interaction" that provides an extremely valuable blueprint for exploring human-computer collaborative composition paradigms.
arXiv:2609.13291v1 Announce Type: cross Abstract: We present ScorePrompts, an interactive system in which users upload a score, receive natural-language descriptions of its musical structure, ask que...
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.
The paper introduces the MATCHA dataset, comprising 1,105 perceptual assessments from 83 experts on attribute-based music matches across five musical attributes—melody, harmony, rhythm, voice, and timbre. A triplet-based forced-choice experiment with 300 cases, including plagiarism, cover songs, and AI-generated music, was used to gather these judgments. Results show measurable agreement among participants and partial alignment with computational similarity measures, highlighting the need for perceptually grounded evaluation in generative AI for music.
The paper studies parameter‑efficient fine‑tuning (PEFT) methods—LoRA and QLoRA—on pretrained music encoders for audio, sheet‑music images, and symbolic scores. It compares full fine‑tuning with PEFT across nine encoders on TriScore and the Musical Theme Dataset, finding that LoRA/QLoRA often match or surpass full fine‑tuning while using far fewer parameters. However, gains in unimodal discrimination do not consistently translate to improved multimodal retrieval, though the adapted-and-projected representations achieve strong piece‑level retrieval performance on TriScore.
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.
arXiv:2607. 22413v1 Announce Type: cross Abstract: Sample retrieval tools can help composers find harmonically compatible material, but querying from a fixed reference sample becomes less informative as arrangements evolve and the harmonic context shifts with each musical decision.
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.
The paper introduces the first general-purpose tokenisation framework for MusicXML and evaluates its impact on deep learning models for symbolic music. By training 26 autoregressive and masked language models, the authors compare MusicXML tokenisation against MIDI and ABC-based representations, exploring different tokenisation strategies and music-grammar-aware approaches. The study demonstrates that MusicXML-tokenised models outperform MIDI and text-based counterparts on both music understanding tasks (composer classification, difficulty estimation, accompaniment suggestion) and generative tasks, as shown by objective metrics and a human preference study.
A tutorial monograph on generative models for music audio covers a wide range of applications—from instrumental clips and full songs with vocals to edits of existing recordings and real‑time accompaniment systems. It explains neural audio codecs, autoencoders, autoregressive and masked token models, diffusion and flow matching, sampling acceleration, and preference optimization, linking training objectives to published systems through worked examples. The book also discusses musical requirements for different tasks, compares representations and methods, and addresses evaluation, data provenance, memorization, attribution, and legal implications.
arXiv:2607. 13587v1 Announce Type: cross Abstract: Automatic symbolic music analysis has made substantial progress, yet existing systems are typically designed for a single mode of use, such as full-score prediction, and therefore do not match the broader range of operations that arise in analysis workflows, including partial completion, local correction, and iterative refinement.
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.