---
title: "SMEBENCH: Benchmarking Neural Music Editing with Synthetized MIDI Edits"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.36715v1"
permalink: "https://feed.astralor.com/items/itm_4231df9e90904351fb11758e"
published: "2026-10-27T06:31:02.000Z"
score: 55
channel: "ai"
tags: ["推理效率","多模态","SMEBENCH","Benchmarking Neural Music","Editing","Synthetized MIDI Edits","Neural","Existing"]
---

# SMEBENCH: Benchmarking Neural Music Editing with Synthetized MIDI Edits

## 速览

Neural music editing requires a system to perform a requested change while preserving the musical content that should remain unchanged. Existing evaluations often lack a paired target edit, making these requirements dif…

## 关键点

- Neural music editing requires a system to perform a requested change while preserving the musical content that should remain unchanged.
- Existing evaluations often lack a paired target edit, making these requirements difficult to measure separately.
- We introduce SMEBench, a large-scale benchmark of controlled music edits constructed by modifying symbolic MIDI performances and rendering matched source and target audio.

## 全文

Neural music editing requires a system to perform a requested change while preserving the musical content that should remain unchanged. Existing evaluations often lack a paired target edit, making these requirements difficult to measure separately. We introduce SMEBench, a large-scale benchmark of controlled music edits constructed by modifying symbolic MIDI performances and rendering matched source and target audio. Each example contains a source, an instruction, a paired target, edit metadata, and complementary descriptions. The benchmark covers twelve instrumentation, articulation, dynamics, and pitch operations and includes a balanced 3,600-example test set together with a smaller real-audio complement derived from multitrack recordings. The paired targets allow source preservation, target agreement, and textual compatibility to be evaluated independently. We use these references to diagnose common audio-editing metrics and benchmark six representative editing systems, showing that the metric used to rank a system can materially change the conclusion. The dataset is available at our repository.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_4231df9e90904351fb11758e