GitHub / manansheel1991 / Speech-Enhancement-Project-using-Deep-Learning
This repository has files to train a deep autoencoder on clean speech (from the mozilla common-voice dataset). Then adding gaussian noise to a file, taking its spectrum, and feeding it into the trained autoencoder, to see the result in frequency domain. It also contains a file to reconstruct the output of the autoencoder, writing it to a file for knowing the result of the enhancement provided by the autoencoder.
JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/manansheel1991%2FSpeech-Enhancement-Project-using-Deep-Learning
PURL: pkg:github/manansheel1991/Speech-Enhancement-Project-using-Deep-Learning
Stars: 2
Forks: 0
Open issues: 0
License: None
Language: Python
Size: 521 KB
Dependencies parsed at: Pending
Created at: about 5 years ago
Updated at: over 3 years ago
Pushed at: about 5 years ago
Last synced at: over 2 years ago
Topics: audio-processing, autoencoders, deep-learning, signal-processing, speech-enhancement