探索面向艺术的XAI：解释生成音乐中的潜空间
Exploring XAI for the Arts: Explaining Latent Space in Generative Music
AI总结：
本文通过扩展MeasureVAE音乐生成模型，利用潜空间正则化、实时交互反馈和属性可视化三种手段提升可解释性，从而弥合潜空间与音乐输出之间的差距，使模型更易理解和调试。
摘要：
可解释人工智能有潜力支持更具交互性和流动性的共创AI系统，使其能够与人进行创造性协作。为此，创造性AI模型需要通过提供可检查、可理解和可修改的可解释AI（XAI）功能来便于调试。然而，目前针对艺术的XAI研究非常少。在本工作中，我们展示了如何使一个用于音乐生成的潜变量模型更具可解释性；具体而言，我们扩展了生成音乐小节的MeasureVAE模型。我们通过以下方式提高模型的可解释性：i）使用潜空间正则化，强制潜空间的某些特定维度映射到有意义的音乐属性；ii）提供用户界面反馈回路，使人们能够调整潜空间的维度并实时观察这些变化的结果；iii）提供潜空间中音乐属性的可视化，帮助人们理解和预测潜空间维度变化的效果。我们认为，通过这样做，我们以一种有意义的方式弥合了潜空间与生成的音乐结果之间的差距，使模型及其输出更具可解释性和可调试性。
英文摘要：
Explainable AI has the potential to support more interactive and fluid co-creative AI systems which can creatively collaborate with people. To do this, creative AI models need to be amenable to debugging by offering eXplainable AI (XAI) features which are inspectable, understandable, and modifiable. However, currently there is very little XAI for the arts. In this work, we demonstrate how a latent variable model for music generation can be made more explainable; specifically we extend MeasureVAE which generates measures of music. We increase the explainability of the model by: i) using latent space regularisation to force some specific dimensions of the latent space to map to meaningful musical attributes, ii) providing a user interface feedback loop to allow people to adjust dimensions of the latent space and observe the results of these changes in real-time, iii) providing a visualisation of the musical attributes in the latent space to help people understand and predict the effect of changes to latent space dimensions. We suggest that in doing so we bridge the gap between the latent space and the generated musical outcomes in a meaningful way which makes the model and its outputs more explainable and more debuggable.
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。
