paper-with-me

Papers

Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information

2018-11-05 · Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis

We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information. We use a deep clustering approach which trains on multi-channel mixtures and learns to project spectrogram bins to source clusters that correlate with various spatial features. We show that using such a training process we can obtain separation performance that is as good as making use of ground truth separation information. Once trained, this system is capable of performing sound separation on monophonic inputs, despite having learned how to do so using multi-channel recordings.

📄 PDF Abstract BibTeX arXiv:1811.01531

Code (1)

etzinis/unsupervised_spatial_dc 공식 구현 pytorch

Tasks

ClusteringDeep ClusteringMulti-Speaker Source SeparationSpeech Separation

Similar Papers 제목 키워드 기반

Bootstrapping single-channel source separation via unsupervised spatial clustering on stereo mixtures

2018-11-06 · Prem Seetharaman, Gordon Wichern, Jonathan Le Roux, Bryan Pardo

Separating an audio scene into isolated sources is a fundamental problem in computer audition, analogous to image segmentation in visual scene analysis. Source separation systems based on deep learning are currently the …

ClusteringImage SegmentationSemantic SegmentationUnsupervised Spatial Clustering

Unsupervised Sound Separation Using Mixture Invariant Training

2020-06-23 · NeurIPS 2020 12 · Scott Wisdom, Efthymios Tzinis, Hakan Erdogan, Ron J. Weiss 외

In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the componen…

Domain AdaptationSpeech EnhancementSpeech SeparationUnsupervised Domain Adaptation

MixCycle: Unsupervised Speech Separation via Cyclic Mixture Permutation Invariant Training

2022-02-08 · Ertuğ Karamatlı, Serap Kırbız

We introduce two unsupervised source separation methods, which involve self-supervised training from single-channel two-source speech mixtures. Our first method, mixture permutation invariant training (MixPIT), enables l…

Data AugmentationSpeech Separation

Spatial Loss for Unsupervised Multi-channel Source Separation

2022-04-01 · Kohei Saijo, Robin Scheibler

We propose a spatial loss for unsupervised multi-channel source separation. The proposed loss exploits the duality of direction of arrival (DOA) and beamforming: the steering and beamforming vectors should be aligned for…

blind source separation

Clustering Mixtures of Bounded Covariance Distributions Under Optimal Separation

2023-12-19 · Ilias Diakonikolas, Daniel M. Kane, Jasper C. H. Lee, Thanasis Pittas

We study the clustering problem for mixtures of bounded covariance distributions, under a fine-grained separation assumption. Specifically, given samples from a $k$-component mixture distribution $D = \sum_{i =1}^k w_i P…

Clustering