论文标题
音乐源分离的元学习提取器
Meta-learning Extractors for Music Source Separation
论文作者
论文摘要
我们提出了一个用于音乐源分离（Meta-Tasnet）的分层元学习启发的模型，其中使用发电机模型预测单个提取器模型的权重。这可以有效地参数共享，同时仍允许特定于仪器的参数化。元数据网被证明比独立或在多任务设置中训练的模型更有效，并实现与最先进方法相当的性能。与后者相比，我们的提取器包含更少的参数，并且运行时性能更快。我们讨论重要的建筑考虑，并探讨这种方法的成本和收益。
We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models. This enables efficient parameter-sharing, while still allowing for instrument-specific parameterization. Meta-TasNet is shown to be more effective than the models trained independently or in a multi-task setting, and achieve performance comparable with state-of-the-art methods. In comparison to the latter, our extractors contain fewer parameters and have faster run-time performance. We discuss important architectural considerations, and explore the costs and benefits of this approach.
