arXiv Machine Learning
Jun 16
Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation
arXiv:2605. 04998v2 Announce Type: replace-cross Abstract: This revision updates a pop-to-jazz chord-generation rehearsal study.
How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
arXiv:2606. 07334v1 Announce Type: cross Abstract: Harmony is a compact symbolic layer where mathematical pitch relations, acoustic consonance, and musical convention meet.
Related stories
arXiv Machine Learning
Aug 31
How Far Should Tokenization Go? Predictive Effectiveness and Relational Losslessness
The paper proposes the Effectiveness–Losslessness Framework to guide tokenization in domains beyond language, using predictive codelength as a criterion. It introduces two boundaries: the Fact–Token Boundary, where observable structure should be encoded into tokens, and the Token–State Boundary, where context‑dependent relations should remain for model state rather than being pre‑tokenized. Experiments on symbolic music show that making musical time explicit and applying tonal‑frame canonicalization improve predictive performance, while fixed pitch coordinates and reversible BPE can increase predictive code length, indicating that carrier compaction alone does not guarantee better predictions.
arXiv AI
Jun 30
LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
arXiv:2606. 30642v1 Announce Type: cross Abstract: Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts.
arXiv Machine Learning
Jun 24
SLEEPING-DISCO 9M: A large-scale pre-training dataset for generative music modeling
arXiv:2506. 14293v4 Announce Type: replace-cross Abstract: We present Sleeping-DISCO 9M, a large-scale pre-training dataset for music and song.
arXiv Machine Learning
1d ago
CHORDONOMICON: A Dataset of 666,000 Songs and their Chord Progressions
Chordonomicon is a new dataset of over 666,000 song-level symbolic chord progressions, each annotated with structural parts such as verse, chorus, and bridge, as well as genre and release date. The dataset was compiled by scraping user-generated progressions from multiple sources and shows strong similarity to established prior datasets. The authors also provide a reproducible benchmark suite for next chord prediction, evaluating RNN, GRU, and LSTM models across various context windows and data scales, and find that structural part annotations consistently improve prediction performance.
arXiv AI
Aug 5
Equivariant Music Transformer
arXiv:2608. 03920v1 Announce Type: cross Abstract: Humans recognize a musical passage even when it is shifted in time or transposed in pitch, indicating a notion of equivariance in the representation space.
arXiv AI
Aug 7
Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset
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.
arXiv Machine Learning
Jul 7
Taste-aware music retrieval from audio embeddings
arXiv:2607. 03296v1 Announce Type: cross Abstract: Crossmodal correspondences between sound and taste are well established in psychology and neuroscience, but largely absent from content-based multimedia retrieval.
arXiv AI
Sep 16
MUUNRiver-Bench: Diagnosing Relation-Dependent Music Retrieval with Multimodal Instructions
MUUNRiver-Bench is a diagnostic benchmark for music retrieval that uses natural‑language instructions to define relevance for reference‑audio queries. It contains 3,440 tracks across 13 genres and 116 sub‑genres and covers seven tasks such as similar‑music, style‑preserving lyric‑rewriting, cover, and segment retrieval. Experiments with six models in eight configurations show that acoustic encoders favor local identity while text‑aligned encoders favor semantic relations, and that instruction‑aware and audio‑text fusion systems do not consistently outperform their backbones.
arXiv AI
Aug 19
Why GPT-Style Models Do Not Directly Transfer to Symbolic Music: Compression in the Wrong Coordinate System
The paper explains why GPT‑style language models fail to transfer directly to symbolic music. It argues that success in language comes from tokenization that compresses data by creating a coordinate system where recurring patterns become predictable. For music, the authors propose that tokenization must build a predictively effective, relationally lossless coordinate system—defining Fact–Token and Token–State boundaries—to enable compression without sacrificing contextual freedom. Controlled experiments confirm that proper coordinate construction improves predictive compressibility, whereas mere sequence compaction does not.
arXiv Machine Learning
Jul 17
MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music
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 AI
Jun 3
Tonal parsimony in chord-sequence analysis: combining modulation cost and tonal vocabulary
arXiv:2606. 03459v1 Announce Type: cross Abstract: We study the assignment of local tonalities to chord sequences, a task useful for harmonic analysis, composition, and jazz-oriented improvisation.