SEGAN: Speech Enhancement Generative Adversarial Network

by   Santiago Pascual, et al.
Universitat Politècnica de Catalunya

Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.


page 1

page 2

page 3

page 4


Language and Noise Transfer in Speech Enhancement Generative Adversarial Network

Speech enhancement deep learning systems usually require large amounts o...

On the Use of Audio Fingerprinting Features for Speech Enhancement with Generative Adversarial Network

The advent of learning-based methods in speech enhancement has revived t...

iSEGAN: Improved Speech Enhancement Generative Adversarial Networks

Popular neural network-based speech enhancement systems operate on the m...

Whispered-to-voiced Alaryngeal Speech Conversion with Generative Adversarial Networks

Most methods of voice restoration for patients suffering from aphonia ei...

DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network for Speech Enhancement

Generative adversarial network (GAN) still exists some problems in deali...

Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement

Speech enhancement is a crucial task for several applications. Among the...

Improving GANs for Speech Enhancement

Generative adversarial networks (GAN) have recently been shown to be eff...

Code Repositories


Speech Enhancement Generative Adversarial Network in TensorFlow

view repo

Please sign up or login with your details

Forgot password? Click here to reset