Skip to content

This module has a neural network implementation for sound source separation

Notifications You must be signed in to change notification settings

fernando79513/dnn-ssl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DNN SSL

This module has a neural network implementation for sound source separation

The neural network architecture used for sound source localization is inspired by the D-ASR network. This network consists of two sections, one with convolutional neural networks (CNNs) and the other with BLSTM networks. The first section takes the phase map of an audio segment as input. This phase map corresponds to the imaginary part of the STFT of that segment. Each microphone produces a phase map, and the convolutional network reduces them to a single tensor.

About

This module has a neural network implementation for sound source separation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages