用于单声道歌唱声分离的渐进多分辨率池CNN
Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation
摘要：
单声道歌唱声分离是一项具有挑战性的任务，已经研究了几十年。深度神经网络（DNN）是MSVS的当前最先进的方法。然而，现有的DNN通常是手动设计的，这是耗时且容易出错的。此外，网络架构通常是预定义的，并且不适应训练数据。为了解决这些问题，我们引入了一个神经结构搜索（NAS）方法的结构设计的DNN MSVS。具体来说，我们提出了一种新的多分辨率卷积神经网络（CNN）框架MSVS即多分辨率池化CNN（MRP-CNN），它使用不同大小的池化算子来提取多分辨率特征。基于NAS，我们然后开发了一个不断发展的框架，即进化MRP-CNN（E-MRP-CNN），通过使用遗传算法自动搜索有效的MRP-CNN结构，优化的单目标只考虑分离性能，或多目标考虑分离性能和模型的复杂性。多目标E-MRP-CNN给出了一组Pareto最优解，每个解都提供了分离性能和模型复杂性之间的权衡。MIR-1 K和DSD 100数据集的定量和定性评价被用来证明拟议的框架的优势，最近的几个基线。
英文摘要：
Monaural Singing Voice Separation (MSVS) is a challenging task and has been studied for decades. Deep neural networks (DNNs) are the current state-of-the-art methods for MSVS. However, the existing DNNs are often designed manually, which is time-consuming and error-prone. In addition, the network architectures are usually pre-defined, and not adapted to the training data. To address these issues, we introduce a Neural Architecture Search (NAS) method to the structure design of DNNs for MSVS. Specifically, we propose a new multi-resolution Convolutional Neural Network (CNN) framework for MSVS namely Multi-Resolution Pooling CNN (MRP-CNN), which uses various-size pooling operators to extract multi-resolution features. Based on the NAS, we then develop an evolving framework namely Evolving MRP-CNN (E-MRP-CNN), by automatically searching the effective MRP-CNN structures using genetic algorithms, optimized in terms of a single-objective considering only separation performance, or multi-objective considering both the separation performance and the model complexity. The multi-objective E-MRP-CNN gives a set of Pareto-optimal solutions, each providing a trade-off between separation performance and model complexity. Quantitative and qualitative evaluations on the MIR-1K and DSD100 datasets are used to demonstrate the advantages of the proposed framework over several recent baselines.
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。
