生成式音乐模型在情绪条件跟随方面的表现如何？
How Well Do Generative Music Models Follow Emotion Conditioning?
浏览论文内容
中文总结 AI 辅助
本研究构建统一评估流程，以GTZAN数据集为基础，评估Stable Audio Open等三个生成式音乐模型的情绪跟随表现，发现文本条件生成更优，效价保留更可靠，强调直接评估情感可控性的重要性。
中文摘要 AI 辅助
近期的生成式音乐模型通过文本和音频条件提供了日益精细的控制，但它们遵循预期情绪线索的忠实程度仍是一个未解决的问题。我们针对生成音乐的情绪跟随问题，提出了一套统一的评估流程。我们使用GTZAN数据集中的全部1000首曲目，借助音频字幕模型DashengLM提取语义音频描述，同时利用音乐情感识别模型Music2Emotion估算源曲目的效价与唤醒度。我们将这些描述与排名靠前的情绪标签相结合，构建出感知情感的文本提示，并使用三个系统生成30秒的音频输出，分别是Stable Audio Open、MusicGen和InspireMusic，同时评估文本条件和音频条件下的生成效果。为衡量情绪跟随程度，我们计算生成音频的效价与唤醒度，并在效价-唤醒度空间中使用绝对误差和欧氏距离将其与源曲目进行比较。结果显示，文本条件下的生成效果始终优于音频条件，其中MusicGen（文本）和InspireMusic（文本）表现最佳，而音频条件的变体稳定性较差。我们还发现，效价的保留比唤醒度更可靠，且情绪跟随程度在不同音乐类型间存在显著差异。这些发现强调了直接评估情感可控性的重要性，而非仅依赖通用质量或提示相关性指标。
英文摘要
Recent generative music models offer increasingly fine-grained control through text and audio conditioning, yet how faithfully they follow intended emotional cues remains an open question. We address this gap with a unified evaluation pipeline for emotion-following in generated music. Using all 1000 tracks in GTZAN, we extract semantic audio descriptions with DashengLM, an audio captioning model, and estimate source-track valence and arousal with Music2Emotion, a music emotion recognition model. We construct affect-aware text prompts by combining descriptions with top-ranked emotion tags and generate 30-second outputs with three systems, Stable Audio Open, MusicGen, and InspireMusic, evaluating both text- and audio-conditioned generation. To measure emotion-following, we compute valence and arousal on generated audio and compare them with the source tracks using absolute error and Euclidean distance in valence-arousal space. Text-conditioned generation consistently outperforms audio conditioning, with MusicGen (text) and InspireMusic (text) achieving the best performance, while audio-conditioned variants prove less stable. We further find that valence is preserved more reliably than arousal and that emotion-following varies substantially across genres. These findings underscore the importance of evaluating affective controllability directly rather than relying solely on general quality or prompt-relevance metrics.
