用重建约束学习音乐片段的紧凑表示，提升和声与节奏理解效果。
ARIMA: Reconstruction-Grounded Predictive Representation Learning for Symbolic Music
- 以固定时长窗口为单位，通过重建与预测联合训练，直接学连续隐表示。
- 在和声、节奏及跨演奏检索任务上表现优异，优于大模型基线。
- 无需显式正则化即可稳定学习，适合音乐理解与生成任务研究者。
符号音乐的自监督学习主要依赖词元级预训练，但这类表示受限于分词器生成序列，且时间跨度级嵌入间接获得。本文提出ARIMA，一种基于重建的潜在预测框架，可直接从数据中学习紧凑的窗口级表示。ARIMA将每个固定时长窗口编码为连续隐表示，通过对比下一隐表示预测进行因果建模，并以结构化重建约束编码器。该设计既保留局部音乐细节，又建模跨窗口的时序演进。我们在涵盖不同层次音乐理解的下游任务上评估ARIMA。结果表明，其在和声、节奏及跨演奏检索任务上尤为高效有效，而在其他任务上仍保持与更大规模基线相当的性能。消融实验进一步显示，下一隐表示预测对时序融合表示至关重要，而结构化重建可稳定隐空间学习，无需显式方差正则化。代码已开源：https://github.com/AndyWeasley2004/symbolic_music_wm。
原文摘要 · Abstract (English)
Self-supervised learning for symbolic music has advanced largely through token-level pretraining, but such representations remain tied to tokenizer-specific sequences and often provide time-span-level embeddings only indirectly. In this paper, we propose ARIMA, a reconstruction-grounded latent predictive framework for symbolic music that learns compact window-based representations directly from data. ARIMA encodes each fixed-duration window into a continuous latent representation, trains a causal predictor with contrastive next-latent prediction, and grounds the encoder through structured reconstruction of music elements. This design preserves local musical details while modeling temporal progression across windows. We evaluate ARIMA on downstream tasks spanning various levels of music understanding. Results show that ARIMA is particularly efficient and effective on tasks involving harmonic, timing, and cross-performance retrieval, while remaining competitive with much larger baselines on other tasks. Ablations further show that next-latent prediction is essential for temporally integrated representations, and that structured reconstruction stabilizes latent learning without requiring explicit variance regularization. The code is at https://github.com/AndyWeasley2004/symbolic_music_wm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。