Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis

2015/03/19 by Andrew J. R. Simpson, Simpson, Andrew J. R.
Computer Science · #68Txx #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Sound (cs.SD) #cs.LG #cs.NE #cs.SD #msc:68Txx

paper · pdf · doi:10.48550/arxiv.1503.05849

arxiv created 2015/03/19 · arxiv updated 2015/03/20

Abstract

In the process of recording, storage and transmission of time-domain audio signals, errors may be introduced that are difficult to correct in an unsupervised way. Here, we train a convolutional deep neural network to re-synthesize input time-domain speech signals at its output layer. We then use this abstract transformation, which we call a deep transform (DT), to perform probabilistic re-synthesis on further speech (of the same speaker) which has been degraded. Using the convolutive DT, we demonstrate the recovery of speech audio that has been subject to extreme degradation. This approach may be useful for correction of errors in communications devices.

Related

• Deep Transform: Cocktail Party Source Separation via Probabilistic Re-Synthesis
• A Generative Model for Raw Audio Using Transformer Architectures
• A Speech Enhancement Method Using Fast Fourier Transform and Convolutional Autoencoder
• Audio Super Resolution using Neural Networks
• On the Design of Deep Priors for Unsupervised Audio Restoration