Problem
Research questions and friction points this paper is trying to address.
music retrieval
relation-dependent
natural-language instructions
multimodal
MUUNRiver-Bench: Diagnosing Relation-Dependent Music Retrieval with Multimodal Instructions
🤖 AI Summary
研究针对音乐检索中关系依赖性问题，通过MUUNRiver-Bench基准，使用多模态指令来定义相关性，揭示了不同模型在处理特定任务时的偏好差异。
📝 Abstract
Music retrieval is relation-dependent: given a reference track, a listener may seek its style with a new theme, a cover, or a comparable voice, and these intents demand contradictory rankings. We present MUUNRiver-Bench, a diagnostic benchmark whose reference-audio queries use natural-language instructions to define relevance. A pipeline combining expert genre priors, LLM-generated prompts and lyrics, synthesis, and expert review yields 3,440 tracks spanning 13 genres and 116 sub-genres, and seven tasks: similar-music, style-preserving lyric-rewriting, lyric-preserving style-rewriting, cover, vocal-timbre, isolated-vocal, and segment retrieval. Across six models in eight configurations, task-wise rank reversals reveal complementary biases: acoustic encoders favour local identity, whereas text-aligned encoders favour semantic relations. Frozen encoders diagnose default similarity preferences; instruction-aware and audio-text fusion systems provide exploratory tests of textual conditioning, with neither simple fusion scheme consistently improving its backbone
Innovation
Methods, ideas, or system contributions that make the work stand out.
natural-language instructions
multimodal music retrieval
genre priors
task-wise rank reversals
acoustic and text-aligned encoders
🔎 Similar Papers
No similar papers found.
