用分源技术提升鼓组转录真实度，输出更精细的7类鼓音符和速度信息。
Enhanced Automatic Drum Transcription via Drum Stem Source Separation
- 将鼓音源分离结果用于扩展转录类别至7类，比传统5类更细致。
- 基于分离出的音源估计MIDI力度值，提升转录表现力。
- 适合音乐制作与音乐信息检索场景，生成更逼真的MIDI数据。
自动鼓组转录（ADT）在音乐信息检索领域仍具挑战性，但近期进展已实现通过ADTOF工具包对最多5类鼓音（底鼓、军鼓、踩镲、桶鼓和吊镲）进行高精度转录。同时，开源社区中已有多个鼓组分源模型可分离超过6类音轨，包括独立的碎音镲和骑镲。本文探索将这些工具结合以提升转录结果的真实性。提出一种简单后处理方法，将转录输出从5类扩展至7类，并基于分离出的音源估计MIDI力度值。在8类鼓转录基线测试中表现优异，生成的MIDI转录具备较高真实性，适用于音乐信息检索或音乐制作任务。
原文摘要 · Abstract (English)
Automatic Drum Transcription (ADT) remains a challenging task in MIR but recent advances allow accurate transcription of drum kits with up 5 classes - kick, snare, hi-hats, toms and cymbals - via the ADTOF package. In addition, several drum kit \emph{stem} separation models in the open source community support separation for more than 6 stem classes, including distinct crash and ride cymbals. In this work we explore the benefits of combining these tools to improve the realism of drum transcriptions. We describe a simple post-processing step which expands the transcription output from five to seven classes and furthermore, we are able to estimate MIDI velocity values based on the separated stems. Our solution achieves strong performance when assessed against a baseline of 8-class drum transcription and produces realistic MIDI transcriptions suitable for MIR or music production tasks.
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。