Learning musical structure with machines

用机器学习音乐结构

• 批准号: 298327-2007
• 负责人: Eck, Douglas
• 金额: $ 1.6万
• 依托单位: Université de Montréal
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2007
• 资助国家: 加拿大
• 起止时间: 2007-01-01 至 2008-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=363335
• 关键词: Learning; musical; structure; machines

Music sequences are difficult or impossible to learn using standard time-series analysis techniques. This is due to the fact that musical structure is elaborated over long time spans and is hierarchical, making it difficult or impossible to learn from local information. By example compare the phrase "John ate the >" to the musical sequence "B C E >" In the linguistic case, the words "John ate the" constrain the possible values of next word >.  In the musical case, the nearby notes "B" "C" and "E" do little to constrain what can come next.  This is not to say that music lacks constraints.  In music the constraints come from elaboration and repetition within the context of musical structure.  Unfortunately (for standard sequence learning tools, at least) this structure is elaborated over long time spans and at different timescales in parallel. I propose an investigation of how music is structured in time and how music structure can be used to constrain machine learning algorithms applied in the domain of music. The two-fold goal of the research is to (a) further our understanding of how music is structured and how music structure relates to music perception and production and to (b) improve the state-of-the-art for machine learning algorithms for two important music-related tasks: human-realistic music performance generation and music sequence learning. I will also address related tasks such as music classification, music similarity measurement and online processing methods for collaboration with real musicians. The key idea behind all of this research is that a better understanding of how music is structured in time will lead directly to better machine learning algorithms for music-related tasks. This work should have impact in machine learning, audio signal processing and music cognition. Portions of this research should be relevant in domains dealing with speech, video and related time series.

使用标准的时间序列分析技术很难或不可能学习音乐序列。这是因为音乐结构是在很长的时间跨度内精心设计的，而且是分等级的，因此很难或不可能从当地信息中学习。例如，将短语“John at the&gt；”与音乐序列“B C E&gt；”进行比较。在语言学的情况下，单词“John ate the”限制了下一个单词&gt；的可能值。在音乐方面，附近的音符“B”、“C”和“E”几乎没有约束接下来会发生什么。但这并不是说音乐缺乏约束。在音乐中，约束来自音乐结构的阐述和重复。不幸的是(至少对于标准序列学习工具而言)这种结构是在很长的时间跨度和不同的时间尺度上并行地阐述的。我建议调查音乐是如何在时间上构造的，以及如何使用音乐结构来约束应用于音乐领域的机器学习算法。这项研究的双重目标是：(A)加深我们对音乐结构以及音乐结构与音乐感知和产生的关系的理解，以及(B)改进机器学习算法的最新水平，用于两个与音乐相关的重要任务：逼真的音乐表演生成和音乐序列学习。我还将讨论相关的任务，如音乐分类、音乐相似性测量和在线处理方法，以便与真正的音乐家合作。所有这项研究背后的关键思想是，更好地理解音乐是如何在时间上构成的，将直接导致更好的机器学习算法来完成与音乐相关的任务。这项工作应该会对机器学习、音频信号处理和音乐认知产生影响。这项研究的部分内容应该与涉及语音、视频和相关时间序列的领域相关。