← Back to all news
arXiv Machine Learning By Saanvi Raghavendran (Abstract Math Institute), Abhishek Bhattacharjee (Abstract Math Institute)

Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models

Read the original on arXiv Machine Learning →

arXiv:2609. 01064v1 Announce Type: cross Abstract: Reconstructing a damaged musical fragment is an inverse problem: the observed sequence contains partial information, while a raga encodes constraints limiting allowable completions.

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
Aug 20

Whole-Piece Training for Symbolic Music Language Models via Full-Horizon Compressed Recurrence

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.

By Yungang Yi, Weihua Li, Matthew Kuo, Catherine Shi, Quan Bai
llms
More like this →
arXiv AI
Jul 16

From Prediction to Collaboration: Interactive Symbolic Music Analysis

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.

By Emmanouil Karystinaios, Johannes Hentschel, Markus Neuwirth, Gerhard Widmer
benchmarks
More like this →