arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.02644cs.SDcs.CLcs.LGeess.AS
收藏

计算和存储高效的通用声音声源分离

Compute and memory efficient universal sound source separation

University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Adobe Research(Adobe研究公司)

Efthymios Tzinis, Zhepei Wang, Xilin Jiang, Paris Smaragdis

摘要:

由深度学习引领的音频声源分离的最新进展使许多神经网络模型能够为这个基本估计问题提供鲁棒的解决方案。在这项研究中,我们提供了一个家庭的通用音频声源分离的高效神经网络架构,同时专注于多个计算方面,阻碍了神经网络在现实世界的场景中的应用。该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。这种机制使我们的模型能够在各种各样的设置中获得高保真信号分离,其中存在可变数量的源,并且具有有限的计算资源(例如浮点运算,内存占用,参数数量和延迟)。我们的实验表明,SuDoRM-RF模型的性能优于甚至超过了几个最先进的基准测试,具有更高的计算资源需求。SuDoRM-RF的因果变化能够在实时语音分离中获得约10 dB标度不变信号失真比改善(SI-SDRi)的竞争性能,同时保持比笔记本电脑设备上的实时速度快20倍。

英文摘要:

Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network architectures for general purpose audio source separation while focusing on multiple computational aspects that hinder the application of neural networks in real-world scenarios. 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. This mechanism enables our models to obtain high fidelity signal separation in a wide variety of settings where variable number of sources are present and with limited computational resources (e.g. floating point operations, memory footprint, number of parameters and latency). Our experiments show that SuDoRM-RF models perform comparably and even surpass several state-of-the-art benchmarks with significantly higher computational resource requirements. The causal variation of SuDoRM-RF is able to obtain competitive performance in real-time speech separation of around 10dB scale-invariant signal-to-distortion ratio improvement (SI-SDRi) while remaining up to 20 times faster than real-time on a laptop device.

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。

↑