# Improving Deep Speech Denoising by Noisy2Noisy Signal Mapping

arXiv: https://arxiv.org/abs/1904.12069 · HTML: https://mlsanity.com/paper/1904.12069/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders](https://mlsanity.com/paper/2106.12271/) (2021)
- [Speech Denoising Without Clean Training Data: A Noise2Noise Approach](https://mlsanity.com/paper/2104.03838/) (2021)
- [BirdSoundsDenoising: Deep Visual Audio Denoising for Bird Sounds](https://mlsanity.com/paper/2210.10196/) (2022)
- [Training Speech Enhancement Systems with Noisy Speech Datasets](https://mlsanity.com/paper/2105.12315/) (2021)
- [Unsupervised speech enhancement with deep dynamical generative speech and noise models](https://mlsanity.com/paper/2306.07820/) (2023)
- [Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems](https://mlsanity.com/paper/2409.01813/) (2024)

## Abstract (arXiv)

Existing deep learning-based speech denoising approaches require clean speech signals to be available for training. This paper presents a deep learning-based approach to improve speech denoising in real-world audio environments by not requiring the availability of clean speech signals in a self-supervised manner. A fully convolutional neural network is trained by using two noisy realizations of the same speech signal, one used as the input and the other as the output of the network. Extensive experimentations are conducted to show the superiority of the developed deep speech denoising approach over the conventional supervised deep speech denoising approach based on four commonly used performance metrics and also based on actual field-testing outcomes.