How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling

• URL: http://arxiv.org/abs/2606.07334v2
• Date: Thu, 11 Jun 2026 10:57:02 GMT
• Title: How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling
• Abstract summary: This report treats chord-symbol sequences as an interpretable, controllable time series for genre-local harmonic modeling.<n>Main evaluation compares LoRA, IA3, BitFit, prefix tuning, and full fine-tuning over 11 genres and 3 seeds, a complete 165-cell grid.<n> chord-symbol adaptation reliably improves genre-local harmonic prediction, but chord symbols alone do not carry complete genre identity.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This report treats chord-symbol sequences as an interpretable, controllable time series for genre-local harmonic modeling. The frozen Music Transformer base - released as a pop-jazz fine-tune endpoint but verified in this revision weight-identical to the pop-only Phase-0 baseline, so all gains are measured over a pure-pop prior (see Changes in v2) - is extended to eleven target genres: blues, bossa nova, Bach chorales, country, electronic, folk, funk, gospel, hip-hop, R&B/soul, and rock. The main evaluation compares LoRA, IA3, BitFit, prefix tuning, and full fine-tuning over 11 genres and 3 seeds, a complete 165-cell grid. All five methods improve over the frozen base on held-out chord prediction (macro gains +2.89 to +3.61 percentage points); LoRA and IA3 score highest, but pairwise Wilcoxon tests with Holm and Benjamini-Hochberg correction do not support a decisive winner. A matched-data-size control sharpens this: at a common corpus size IA3 stays on top while LoRA drops to last, so the small method gaps are partly data-driven rather than representational. A control-token baseline is also strong, and wrong-genre adapters often beat the frozen base, suggesting the adaptation effect is largely lightweight conditioning over a reusable harmonic base rather than genre-specific adapter memory. Further diagnostics (rank sweeps, wrong-genre rotation, a base-checkpoint ablation that v2 reinterprets as a same-weights control, chord-only genre classification, output-distribution statistics, real-song evaluation, duplicate analysis) support a bounded conclusion: chord-symbol adaptation reliably improves genre-local harmonic prediction, but chord symbols alone do not carry complete genre identity. Perceived genre authenticity and musical quality are left to controlled listener evaluation.

Related papers

• Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth [50.62320148925983]
  Vision--language models (VLMs) can answer chart questions accurately, but output accuracy does not show how they combine the evidence needed to recover an exact value.<n>We study vertical-bar value reading with controlled counterfactual activation patching in Qwen2.5VL-7B-Instruct and InternVL3.5-8B.
  arXiv  Detail & Related papers  (2026-09-12T06:28:11Z)
• Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action Models [10.591519354017803]
  We show how to repair two blind spots in a vision--action (VLA) policy.<n>We use a drop-in module to fine-tune a pretrained VLA.<n>We show how TFGCA improves in-distribution LIBERO by +1.5 on average, the OOD LIBERO-Plus by +6.3, the randomized average under RoboTwin domain randomization by +28.5, and the overall success rate on three real-robot AgiBot A2 tasks by +11.67 points.
  arXiv  Detail & Related papers  (2026-09-09T09:16:49Z)
• Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights [0.40611352512781873]
  We introduce a Rater Ising-Potts model that uses agreement indicators between ratings and category labels.<n>We evaluate the model on three constructed-response datasets spanning a corpus of K=14,466 short answers on a three-level rubric and two AERA essay prompts of roughly 1,200-1,400 responses on four-point rubrics.
  arXiv  Detail & Related papers  (2026-09-08T14:26:19Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• FIGMA: Towards FIne-Grained Music retrievAl [65.98380295254817]
  Retrieving music using natural language descriptions has improved with contrastive audio-text models such as CLAP, but current systems remain limited to coarse semantic queries.<n>We show that this limitation stems from the contrastive learning objective itself: despite being trained on long captions, CLAP-based models effectively utilize only the first few tokens.<n>We propose FIGMA, a multi-view contrastive architecture that addresses this limitation by jointly optimizing global audio-text alignment and frame-level, token-wise alignment.
  arXiv  Detail & Related papers  (2026-06-04T18:05:39Z)
• STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts [0.0]
  We present STRUM, an audio-to-chart pipeline that converts raw recordings into playable Clone Hero charts for drums, guitar, bass, vocals, and keys without any oracle metadata.<n>We report a complete ablation of seven drum-pipeline components with paired per-song Wilcoxon tests, an analysis of ground-truth-to-audio timing distributions in community Clone Hero charts, and a per-class confusion matrix for the drum.
  arXiv  Detail & Related papers  (2026-05-12T13:56:09Z)
• Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation [0.0]
  Chord progression generation is practically important but understudied.<n>This paper treats chord generation as a standalone task and addresses a question that arises whenever such a model is adapted across genres.
  arXiv  Detail & Related papers  (2026-05-06T14:59:37Z)
• Adaptive Accompaniment with ReaLchords [60.690020661819055]
  We propose ReaLchords, an online generative model for improvising chord accompaniment to user melody.<n>We start with an online model pretrained by maximum likelihood, and use reinforcement learning to finetune the model for online use.
  arXiv  Detail & Related papers  (2025-06-17T16:59:05Z)
• Evaluation of pretrained language models on music understanding [0.0]
  We demonstrate that Large Language Models (LLM) suffer from 1) prompt sensitivity, 2) inability to model negation, and 3) sensitivity towards the presence of specific words. We quantified these properties as a triplet-based accuracy, evaluating the ability to model the relative similarity of labels in a hierarchical ontology. Despite the relatively high accuracy reported, inconsistencies are evident in all six models, suggesting that off-the-shelf LLMs need adaptation to music before use.
  arXiv  Detail & Related papers  (2024-09-17T14:44:49Z)
• An End-to-End Approach for Chord-Conditioned Song Generation [14.951089833579063]
  Song Generation task aims to synthesize music composed of vocals and accompaniment from given lyrics. To mitigate the issue, we introduce an important concept from music composition, namely chords to song generation networks. We propose a novel model termed Chord-Conditioned Song Generator (CSG) based on it.
  arXiv  Detail & Related papers  (2024-09-10T08:07:43Z)
• Confidence-Based Model Selection: When to Take Shortcuts for Subpopulation Shifts [119.22672589020394]
  We propose COnfidence-baSed MOdel Selection (CosMoS), where model confidence can effectively guide model selection. We evaluate CosMoS on four datasets with spurious correlations, each with multiple test sets with varying levels of data distribution shift.
  arXiv  Detail & Related papers  (2023-06-19T18:48:15Z)
• Simple and Controllable Music Generation [94.61958781346176]
  MusicGen is a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns.
  arXiv  Detail & Related papers  (2023-06-08T15:31:05Z)
• Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation [138.74751744348274]
  We propose Museformer, a Transformer with a novel fine- and coarse-grained attention for music generation. Specifically, with the fine-grained attention, a token of a specific bar directly attends to all the tokens of the bars that are most relevant to music structures. With the coarse-grained attention, a token only attends to the summarization of the other bars rather than each token of them so as to reduce the computational cost.
  arXiv  Detail & Related papers  (2022-10-19T07:31:56Z)
• Cadence Detection in Symbolic Classical Music using Graph Neural Networks [7.817685358710508]
  We present a graph representation of symbolic scores as an intermediate means to solve the cadence detection task. We approach cadence detection as an imbalanced node classification problem using a Graph Convolutional Network. Our experiments suggest that graph convolution can learn non-local features that assist in cadence detection, freeing us from the need of having to devise specialized features that encode non-local context.
  arXiv  Detail & Related papers  (2022-08-31T12:39:57Z)
• BacHMMachine: An Interpretable and Scalable Model for Algorithmic Harmonization for Four-part Baroque Chorales [23.64897650817862]
  BacHMMachine employs a "theory-driven" framework guided by music composition principles. It provides a probabilistic framework for learning key modulations and chordal progressions from a given melodic line. It results in vast decreases in computational burden and greater interpretability.
  arXiv  Detail & Related papers  (2021-09-15T23:39:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.