Speech Denoising without Clean Training Data: a Noise2Noise Approach

04/08/2021
by   Madhav Mahesh Kashyap, et al.
0

This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples. Conventional wisdom dictates that in order to achieve good speech denoising performance, there is a requirement for a large quantity of both noisy speech samples and perfectly clean speech samples, resulting in a need for expensive audio recording equipment and extremely controlled soundproof recording studios. These requirements pose significant challenges in data collection, especially in economically disadvantaged regions and for low resource languages. This work shows that speech denoising deep neural networks can be successfully trained utilizing only noisy training audio. Furthermore it is revealed that such training regimes achieve superior denoising performance over conventional training regimes utilizing clean training audio targets, in cases involving complex noise distributions and low Signal-to-Noise ratios (high noise environments). This is demonstrated through experiments studying the efficacy of our proposed approach over both real-world noises and synthetic noises using the 20 layered Deep Complex U-Net architecture.

READ FULL TEXT
POST COMMENT

Comments

huan20

Why is that "The variance of the sample distribution Var(m) is equal to the variance of the population divided by the sampling size."? It seems to me that this is not a valid conclusion. However, it is ture that minimizing L2,n2n is minimizing L2,n2c at the same time.

Authors

page 4

10/30/2021

Speech Denoising Using Only Single Noisy Audio Samples

In this paper, we propose a novel Single Noisy Audio De-noising Framewor...
04/26/2019

Self-Supervised Deep Learning-Based Speech Denoising

This paper presents a self-supervised deep neural network solution to sp...
04/16/2019

Audio Denoising with Deep Network Priors

We present a method for audio denoising that combines processing done in...
10/22/2020

Listening to Sounds of Silence for Speech Denoising

We introduce a deep learning model for speech denoising, a long-standing...
02/17/2022

Multi-Channel Speech Denoising for Machine Ears

This work describes a speech denoising system for machine ears that aims...
10/30/2017

Denoising random forests

This paper proposes a novel type of random forests called a denoising ra...
07/10/2018

Deep Learning on Low-Resource Datasets

In training a deep learning system to perform audio transcription, two p...

Code Repositories

Noise2Noise-audio_denoising_without_clean_training_data

Source code for the paper titled "Speech Denoising without Clean Training Data: a Noise2Noise Approach". This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio denoising methods by showing that it is possible to train deep speech denoising networks using only noisy speech samples.


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.