SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision

• 类型：arxiv
• 标识：2610.05336
• 链接：https://arxiv.org/abs/2610.05336
• 主分类：multimodal
• 形态：method
• TLDR：Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation. Automatically annotated MIDI, rendered into audio, provides scalable supervision across music understanding tasks. Task-specific structured decoders integrate complementary mu
• 待LLM分类：否
• 标题中文：SheetSage2：基于合成监督的连贯主旋律谱转录
• TLDR中文：将音乐转录为人类可读的乐谱需要对节奏、和声、旋律与曲式的整体理解。两大障碍限制了这一目标的实现：标注录音稀缺，以及精确的局部预测仍可能产生不一致的音乐序列。本文提出 SheetSage2，一个统一的音乐转录框架，结合合成数据、任务特定的结构化解码与自回归蒸馏。自动标注的 MIDI 渲染为音频后，可为各类音乐理解任务提供可扩展的监督。任务特定的结构化解码器整合互补的音乐……
• 来源文件：
• /inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json