DeepAI AI Chat
Log In Sign Up

Neural separation of observed and unobserved distributions

by   Tavi Halperin, et al.

Separating mixed distributions is a long standing challenge for machine learning and signal processing. Applications include: single-channel multi-speaker separation (cocktail party problem), singing voice separation and separating reflections from images. Most current methods either rely on making strong assumptions on the source distributions (e.g. sparsity, low rank, repetitiveness) or rely on having training samples of each source in the mixture. In this work, we tackle the scenario of extracting an unobserved distribution additively mixed with a signal from an observed (arbitrary) distribution. We introduce a new method: Neural Egg Separation - an iterative method that learns to separate the known distribution from progressively finer estimates of the unknown distribution. In some settings, Neural Egg Separation is initialization sensitive, we therefore introduce GLO Masking which ensures a good initialization. Extensive experiments show that our method outperforms current methods that use the same level of supervision and often achieves similar performance to full supervision.


page 6

page 13


Towards Unsupervised Single-Channel Blind Source Separation using Adversarial Pair Unmix-and-Remix

Unsupervised single-channel blind source separation is a long standing s...

Probabilistic Binary-Mask Cocktail-Party Source Separation in a Convolutional Deep Neural Network

Separation of competing speech is a key challenge in signal processing a...

Contextually Supervised Source Separation with Application to Energy Disaggregation

We propose a new framework for single-channel source separation that lie...

Auditory Separation of a Conversation from Background via Attentional Gating

We present a model for separating a set of voices out of a sound mixture...

Voice Separation with an Unknown Number of Multiple Speakers

We present a new method for separating a mixed audio sequence, in which ...

An Initialization Scheme for Meeting Separation with Spatial Mixture Models

Spatial mixture model (SMM) supported acoustic beamforming has been exte...