腔室环境生成器:通过生成式建模生成无限高质量的MIR数据
The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling
摘要:
数据是现代机器学习系统的生命线,包括音乐信息检索(MIR)系统。然而,MIR长期以来一直被小数据集和不可靠的标签所困扰。在这项工作中,我们建议使用生成建模来打破这一瓶颈。通过将音符的生成模型(在巴赫合唱团上训练的Coconet)与室内合奏的结构化合成模型(在URMP上训练的MIDI-DDSP)流水线化,我们展示了一个能够产生无限数量的具有丰富注释的逼真合唱音乐的系统,所述注释包括混音、词干、连音、音符级性能属性(断奏、颤音等),甚至是细粒度的合成参数(音调、幅度等)。我们称这个系统为腔室合奏生成器(CEG),并使用它来生成一个大的数据集chorales从四个不同的腔室合奏(CocoChorales)。我们证明,使用我们的方法生成的数据改进了最先进的音乐转录和声源分离模型,我们发布的系统和数据集作为开源的基础,为未来的工作在MIR社区。
英文摘要:
Data is the lifeblood of modern machine learning systems, including for those in Music Information Retrieval (MIR). However, MIR has long been mired by small datasets and unreliable labels. In this work, we propose to break this bottleneck using generative modeling. By pipelining a generative model of notes (Coconet trained on Bach Chorales) with a structured synthesis model of chamber ensembles (MIDI-DDSP trained on URMP), we demonstrate a system capable of producing unlimited amounts of realistic chorale music with rich annotations including mixes, stems, MIDI, note-level performance attributes (staccato, vibrato, etc.), and even fine-grained synthesis parameters (pitch, amplitude, etc.). We call this system the Chamber Ensemble Generator (CEG), and use it to generate a large dataset of chorales from four different chamber ensembles (CocoChorales). We demonstrate that data generated using our approach improves state-of-the-art models for music transcription and source separation, and we release both the system and the dataset as an open-source foundation for future work in the MIR community.
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。