arXiv cs.AI· Josef Pavl\'i\v{c}ek, Martin Pelik\'an·· 12 小时前AI 评分18
冻结版可解释旋律和声器 EMH 在 HookTheory 语料上的和声决策评测
From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory
AI 导读
研究将冻结的可解释旋律和声器 EMH 直接应用于 HookTheory 中旋律与和弦对齐的片段，在不改动规则的情况下评测其和声决策。19 个片段共得到 439 个可评估和声段，和弦完全一致率 20.50%、和弦根音一致率 31.66%、和声功能一致率 47.62%。
正文 · 原文
Abstract:Automatic melody harmonization is often evaluated through individual compositions or data-driven corpus models. This study examines whether an explainable harmonic decision model developed for individual songs can be applied to independently collected human annotations without changing its rules. We evaluate a frozen Explainable Melody Harmonizer (EMH) on selected HookTheory excerpts containing aligned melody and chord annotations. EMH generates chord sequences from melody alone using explicit criteria for melodic compatibility, harmonic function, persistence, cadence, meter-aware segmentation, and Viterbi-like optimization. Human chords are withheld during generation and used only for post-hoc comparison.
Nineteen excerpts yielded 439 evaluable harmonic segments. Exact chord agreement reached 20.50%, chord-root agreement 31.66%, and harmonic-function agreement 47.62%, with functions assessed relative to the key inferred by EMH. Decision-level analysis identified 203 segments (46.24%) where the human chord lay outside the model's candidate vocabulary and 146 (33.26%) where it was available but not selected. These findings distinguish representational limitations from differences in chord selection without treating the human reference as the only musically valid solution. The study demonstrates a reproducible, interpretable approach to corpus-based evaluation of harmonic decision-making.
| Comments: | 10 pages, 3 Figures, 2 tables, source codes in git |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.22416 [cs.SD] |
| (or arXiv:2610.22416v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22416 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Josef Pavlicek Ph.D. [view email]
[v1]
Wed, 14 Oct 2026 23:42:28 UTC (2,318 KB)
来源：arXiv cs.AI · arxiv.org