BASS：用于音乐结构和语义推理的音频语言模型基准测试
BASS: Benchmarking Audio LMs for Musical Structure and Semantic Reasoning
AI总结：
BASS通过评估音频语言模型在音乐结构和语义推理方面的性能，揭示了现有模型在高层次推理任务上的局限性，并为音乐推荐和搜索提供评估框架。
摘要：
音乐理解是一个复杂任务，通常需要在音频的结构和语义元素上进行推理。我们介绍了BASS，旨在评估音频语言模型在音乐理解和推理方面的性能，涵盖四个广泛类别：结构分割、歌词转录、音乐学分析和艺术家合作。BASS包含2658个问题，覆盖12项任务、1993首独特歌曲，涵盖超过138小时的音乐，涵盖广泛流派和曲目，旨在评估音乐学知识和推理能力。我们评估了14个开源和前沿的多模态语言模型，发现即使是最先进的模型在结构分割和艺术家合作等高层次推理任务上也表现不佳，而在歌词转录任务上表现最佳。我们的分析表明，当前模型有效利用了语言先验知识，但在音乐结构、人声和音乐学属性上的推理仍有限。BASS提供了一个评估框架，可广泛应用于音乐推荐和搜索，并有望指导音频语言模型的发展。
英文摘要：
Music understanding is a complex task that often requires reasoning over both structural and semantic elements of audio. We introduce BASS, designed to evaluate music understanding and reasoning in audio language models across four broad categories: structural segmentation, lyric transcription, musicological analysis, and artist collaboration. BASS comprises 2658 questions spanning 12 tasks, 1993 unique songs and covering over 138 hours of music from a wide range of genres and tracks, crafted to assess musicological knowledge and reasoning in real-world scenarios. We evaluate 14 open-source and frontier multimodal LMs, finding that even state-of-the-art models struggle on higher-level reasoning tasks such as structural segmentation and artist collaboration, while performing best on lyric transcription. Our analysis reveals that current models leverage linguistic priors effectively but remain limited in reasoning over musical structure, vocal, and musicological attributes. BASS provides an evaluation framework with widespread applications in music recommendation and search and has the potential to guide the development of audio LMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
