Speech Denoising without Clean Training Data: a Noise2Noise Approach
- URL: http://arxiv.org/abs/2104.03838v1
- Date: Thu, 8 Apr 2021 15:27:49 GMT
- Title: Speech Denoising without Clean Training Data: a Noise2Noise Approach
- Authors: Madhav Mahesh Kashyap, Anuj Tambwekar, Krishnamoorthy Manohara, S
Natarajan
- Abstract summary: This paper tackles the problem of the heavy dependence of clean speech data required by deep learning based audio-denoising methods.
It shows that it is possible to train deep speech denoising networks using only noisy speech samples.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- TRNet: Two-level Refinement Network leveraging Speech Enhancement for Noise Robust Speech Emotion Recognition [29.756961194844717]
The proposed TRNet substantially promotes the robustness of the proposed system in both matched and unmatched noisy environments.
Results validate that the proposed system substantially promotes the robustness of the proposed system in both matched and unmatched noisy environments.
arXiv Detail & Related papers (2024-04-19T16:09:17Z) - Continuous Modeling of the Denoising Process for Speech Enhancement
Based on Deep Learning [61.787485727134424]
We use a state variable to indicate the denoising process.
A UNet-like neural network learns to estimate every state variable sampled from the continuous denoising process.
Experimental results indicate that preserving a small amount of noise in the clean target benefits speech enhancement.
arXiv Detail & Related papers (2023-09-17T13:27:11Z) - Improving Noise Robustness of Contrastive Speech Representation Learning
with Speech Reconstruction [109.44933866397123]
Noise robustness is essential for deploying automatic speech recognition systems in real-world environments.
We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition.
We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
arXiv Detail & Related papers (2021-10-28T20:39:02Z) - Removing Noise from Extracellular Neural Recordings Using Fully
Convolutional Denoising Autoencoders [62.997667081978825]
We propose a Fully Convolutional Denoising Autoencoder, which learns to produce a clean neuronal activity signal from a noisy multichannel input.
The experimental results on simulated data show that our proposed method can improve significantly the quality of noise-corrupted neural signals.
arXiv Detail & Related papers (2021-09-18T14:51:24Z) - Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images [98.82804259905478]
We present Neighbor2Neighbor to train an effective image denoising model with only noisy images.
In detail, input and target used to train a network are images sub-sampled from the same noisy image.
A denoising network is trained on sub-sampled training pairs generated in the first stage, with a proposed regularizer as additional loss for better performance.
arXiv Detail & Related papers (2021-01-08T02:03:25Z) - Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated
Convolutional Kernel Architecture [3.796436257221662]
We propose a dilated convolutional network that satisfies an invariant property, allowing efficient kernel-based training without random masking.
We also propose an adaptive self-supervision loss to circumvent the requirement of zero-mean constraint, which is specifically effective in removing salt-and-pepper or hybrid noise.
arXiv Detail & Related papers (2020-12-07T12:13:17Z) - Enhancing and Learning Denoiser without Clean Reference [23.11994688706024]
We propose a novel deep image-denoising method by regarding the noise reduction task as a special case of the noise transference task.
The results on real-world denoising benchmarks demonstrate that our proposed method achieves promising performance on removing realistic noises.
arXiv Detail & Related papers (2020-09-09T13:15:31Z) - Unpaired Learning of Deep Image Denoising [80.34135728841382]
This paper presents a two-stage scheme by incorporating self-supervised learning and knowledge distillation.
For self-supervised learning, we suggest a dilated blind-spot network (D-BSN) to learn denoising solely from real noisy images.
Experiments show that our unpaired learning method performs favorably on both synthetic noisy images and real-world noisy photographs.
arXiv Detail & Related papers (2020-08-31T16:22:40Z) - DenoiSeg: Joint Denoising and Segmentation [75.91760529986958]
We propose DenoiSeg, a new method that can be trained end-to-end on only a few annotated ground truth segmentations.
We achieve this by extending Noise2Void, a self-supervised denoising scheme that can be trained on noisy images alone, to also predict dense 3-class segmentations.
arXiv Detail & Related papers (2020-05-06T17:42:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.