Sudo RM -RF: Efficient Networks for Universal Audio Source Separation
Sudo RM -RF: Efficient Networks for Universal Audio Source Separation
复制标题
Sudo RM -RF：用于通用音频源分离的高效网络
DOI：
10.1109/mlsp49062.2020.9231900
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Paris Smaragdis
中科院分区：
文献类型：
--
作者：
Efthymios Tzinis;Zhepei Wang;Paris Smaragdis
在本文中，我们提出了一个有效的神经网络端到端的通用音频源分离。具体来说，这个卷积网络的骨干结构是多分辨率特征的连续下采样和恢复（SuDoRM-RF）以及通过简单的一维卷积执行的聚合。通过这种方式，我们能够获得高质量的音频源分离，具有有限数量的浮点运算，内存要求，参数数量和延迟。我们在语音和环境声音分离数据集上的实验表明，SuDoRM - RF的性能优于甚至超过了各种最先进的方法，但计算资源要求明显更高。
In this paper, we present an efficient neural network for end-to-end general purpose audio source separation. Specifically, the backbone structure of this convolutional network is the SUccessive DOwnsampling and Resampling of Multi-Resolution Features (SuDoRM-RF) as well as their aggregation which is performed through simple one-dimensional convolutions. In this way, we are able to obtain high quality audio source separation with limited number of floating point operations, memory requirements, number of parameters and latency. Our experiments on both speech and environmental sound separation datasets show that SuDoRM - RF performs comparably and even surpasses various state-of-the-art approaches with significantly higher computational resource requirements.