当前位置:
X-MOL 学术
›
arXiv.cs.SD
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
arXiv - CS - Sound Pub Date : 2020-07-14 , DOI: arxiv-2007.06833 Efthymios Tzinis, Zhepei Wang and Paris Smaragdis
arXiv - CS - Sound Pub Date : 2020-07-14 , DOI: arxiv-2007.06833 Efthymios Tzinis, Zhepei Wang and Paris Smaragdis
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 (SuDoRMRF) 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 SuDoRMRF performs comparably and even surpasses various state-of-the-art
approaches with significantly higher computational resource requirements.
中文翻译:
Sudo rm -rf:通用音频源分离的高效网络
在本文中,我们提出了一种用于端到端通用音频源分离的高效神经网络。具体来说,这个卷积网络的主干结构是多分辨率特征的 SUccessive DOwnsampling 和 Resampling (SuDoRMRF) 以及它们通过简单的一维卷积执行的聚合。通过这种方式,我们能够在有限数量的浮点运算、内存要求、参数数量和延迟的情况下获得高质量的音频源分离。我们在语音和环境声音分离数据集上的实验表明,SuDoRMRF 的性能相当,甚至超过了具有更高计算资源需求的各种最先进的方法。
更新日期:2020-07-15
中文翻译:
Sudo rm -rf:通用音频源分离的高效网络
在本文中,我们提出了一种用于端到端通用音频源分离的高效神经网络。具体来说,这个卷积网络的主干结构是多分辨率特征的 SUccessive DOwnsampling 和 Resampling (SuDoRMRF) 以及它们通过简单的一维卷积执行的聚合。通过这种方式,我们能够在有限数量的浮点运算、内存要求、参数数量和延迟的情况下获得高质量的音频源分离。我们在语音和环境声音分离数据集上的实验表明,SuDoRMRF 的性能相当,甚至超过了具有更高计算资源需求的各种最先进的方法。