arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.09080cs.SDeess.AS
收藏

用于音乐医学生成的语言模型

Language Models for Music Medicine Generation

University of California Santa Cruz(加州大学圣克鲁兹分校);Johannes Kepler University Linz(林茨约翰内斯·开普勒大学);Liberty Healthcare Corporation(自由医疗保健公司)

Emmanouil Nikolakakis, Joann Ching, Emmanouil Karystinaios, Gabrielle Sipin, Gerhard Widmer, Razvan Marinescu

AI总结:

提出对 MusicGen 进行微调,生成符合同质原则的 30 秒音乐片段,组合成 15 分钟的“音乐药物”,帮助患者过渡情绪状态,作为音乐疗法会话间的临时缓解手段。

摘要:

近年来,音乐疗法已被证明能提供与情绪健康相关的多种健康益处。反过来,保持健康的情绪状态已被证明对接受治疗的患者(如帕金森病患者或承受压力与焦虑的患者)是有效的。我们提出对 MusicGen(一种生成音乐的 transformer 模型)进行微调,以创建短小的音乐片段,帮助患者从负面情绪状态过渡到期望的情绪状态。我们在带有情绪标签的 MTG-Jamendo 数据集上使用低秩分解微调,生成 30 秒的片段,这些片段遵循同质原则,通过效价-唤醒度环状模型引导患者经历中间状态。生成的音乐使用音乐情绪识别模型进行评估,以确保与预期情绪保持一致。通过连接这些片段,我们制作出一段 15 分钟的“音乐药物”,类似于音乐疗法会话。我们的方法是首个利用语言模型生成音乐药物的模型。最终,该输出旨在作为经委员会认证的治疗师进行音乐疗法会话之间的临时缓解手段。

英文摘要:

Music therapy has been shown in recent years to provide multiple health benefits related to emotional wellness. In turn, maintaining a healthy emotional state has proven to be effective for patients undergoing treatment, such as Parkinson's patients or patients suffering from stress and anxiety. We propose fine-tuning MusicGen, a music-generating transformer model, to create short musical clips that assist patients in transitioning from negative to desired emotional states. Using low-rank decomposition fine-tuning on the MTG-Jamendo Dataset with emotion tags, we generate 30-second clips that adhere to the iso principle, guiding patients through intermediate states in the valence-arousal circumplex. The generated music is evaluated using a music emotion recognition model to ensure alignment with intended emotions. By concatenating these clips, we produce a 15-minute "music medicine" resembling a music therapy session. Our approach is the first model to leverage Language Models to generate music medicine. Ultimately, the output is intended to be used as a temporary relief between music therapy sessions with a board-certified therapist.

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。

↑