Multichannel Audio Source Separation With Deep Neural Networks

By Aditya Arie Nugraha, Antoine Liutkus, Emmanuel Vincent. IEEE/ACM Transactions on Audio Speech and Language Processing, 2016

308 citations recorded by the source corpus.

Subfields: Signal Processing

View Paper: https://www.semanticscholar.org/paper/6b03d309551991d3a905ff7a7f4501aa2864b99f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Signal Processing

1. Bo Li
2. Chuang Gan
3. Hang Zhao
4. Tara N. Sainath
5. Tillman Weyde
6. Antonio Torralba
7. Shuo-yiin Chang
8. Tuomas Virtanen

Citations in the corpus

• Improved Speech Enhancement with the Wave-U-Net (2018, background): “Source separation of audio has seen great improvement in recent years through deep learning models 33 [5, 8].”
• Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation (2018, methodology): “To alleviate the problem of fixed spectral representations widely used in previous work [6, 11, 13, 14, 20, 23], an adaptive front-end for spectrogram computation was developed [24] that is trained jointly with the separation network, which operates on the resulting magnitude spectrogram.”
• A Consolidated Perspective on Multimicrophone Speech Enhancement and Source Separation (2017, unknown): “Yet, a few multichannel approaches have recently been proposed that use DNNs in a variety of ways: to estimate the SPP using a DNN and subsequently derive a beamformer [342], to alternately reestimate the source magnitude spectra using DNNs and the spatial covariance matrices in an EM-like fashion [”
• Deep Learning for Audio Signal Processing (2019, background): “to model the single-channel spectrum or the separation mask of a target source [126]; in this case the main role of deep learning is to model the spectral characteristics of the target.”
• Supervised Speech Separation Based on Deep Learning: An Overview (2017, unknown): “[133], who perform array source separation 1348 using DNN for monaural separation and a complex multivariate 1349 Gaussian distribution to model spatial information.”
• Phase-aware Speech Enhancement with Deep Complex U-Net (2019, background): “This has led to the situation where most approaches focus only on the estimation of a magnitude spectrogram while reusing noisy phase information (Huang et al., 2014; Xu et al., 2015; Grais et al., 2016; Nugraha et al., 2016; Takahashi et al., 2018b).”
• Multichannel music separation with deep neural networks (2016, unknown): “The systems for music separation presented in this article are similar to the speech enhancement system in [20].”
• An analysis of environment, microphone and data simulation mismatches in robust speech recognition (2017, unknown): “We considered the DNN-based multichannel source separation technique of Nugraha et al. (2016a).”
• Self-Supervised Moving Vehicle Tracking With Stereo Sound (2019, background): “Using multichannel audio has also been shown to be advantageous in other scenarios, such as sound source separation [27].”