MuseCPBench: an Empirical Study of Music Editing Methods through Music Context Preservation

2025-12-16

AI Summary

Existing music editing methods lack a unified, reproducible evaluation standard for Music Context Preservation (MCP), undermining reliable performance comparison. To address this, we introduce MuseCPBench—the first systematic MCP benchmark—formally defining MCP and establishing a multimodal evaluation protocol spanning melody, harmony, rhythm, and structure. Our framework integrates objective signal-level analysis with controlled subjective assessment. Evaluated across five state-of-the-art baseline models, MuseCPBench comprehensively tests robustness in preserving four critical musical elements. Experimental results reveal significant degradation in all baselines on at least two element categories (average MCP drop of 23.7%), pinpointing structural preservation as a key weakness. This work delivers the first standardized, empirically verifiable evaluation framework for high-fidelity music editing, enabling rigorous benchmarking and guiding principled model improvement.

Technology Category

• Machine Learning: Evaluation and Analysis
• Natural Language Processing: Safety and Robustness
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

Music editing plays a vital role in modern music production, with applications in film, broadcasting, and game development. Recent advances in music generation models have enabled diverse editing tasks such as timbre transfer, instrument substitution, and genre transformation. However, many existing works overlook the evaluation of their ability to preserve musical facets that should remain unchanged during editing a property we define as Music Context Preservation (MCP). While some studies do consider MCP, they adopt inconsistent evaluation protocols and metrics, leading to unreliable and unfair comparisons. To address this gap, we introduce the first MCP evaluation benchmark, MuseCPBench, which covers four categories of musical facets and enables comprehensive comparisons across five representative music editing baselines. Through systematic analysis along musical facets, methods, and models, we identify consistent preservation gaps in current music editing methods and provide insightful explanations. We hope our findings offer practical guidance for developing more effective and reliable music editing strategies with strong MCP capability

Problem

• Evaluates music editing methods for context preservation
• Introduces benchmark for consistent and fair comparisons
• Identifies gaps to guide better music editing strategies

Innovation

• Introduces MuseCPBench benchmark for music editing evaluation
• Covers four musical facets across five editing baselines
• Identifies preservation gaps to guide future strategy development