IP Library › Granted Patent US 12,725,009
Granted Patent B2
US 12,725,009 · App. 18/247,562 · Granted Sep 1, 2026

Noise learning-based denoising autoencoder

Inventors: Woonghee Lee (Seoul, KR); Ursula Challita (Solna, SE); Jingya Li (Gothenburg, SE)
Assignee: Telefonaktiebolaget LM Ericsson (publ)
G06N3/0455G06N3/048
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,725,009
App. No.
18/247,562
Granted
Sep 1, 2026
Kind
B2
Abstract

Methods and apparatuses for noise learning-based denoising of noisy input data Y that is equal to the original data X plus the noise N (i.e., Y=X+N). In contrast with a conventional denoising autoencoder (DAE) method that attempts to learn the original data X directly from noisy input data Y, the noise learning-based denoising learns the noise N in the noisy input data Y and then regenerates the original data X by subtracting the learned noise N from the noisy input data Y. Learning the noise N may include inputting the noisy input data Y into an encoder of a neural network, and the learned noise N may be output from a decoder of the neural network. Training the neural network may include inputting noisy training data into an encoder of the neural network and outputting training noise from a decoder of the neural network.

Claims (318)

1 . A denoising method comprising:

inputting noisy input data Y into an encoder of a neural network of a noise learning-based denoising autoencoder (nlDAE);

using the neural network of the nlDAE to learn noise N in the noisy input data Y;

outputting the learned noise N from a decoder of the neural network of the nlDAE; and

using a subtractor of the nlDAE to regenerate original data X by subtracting the learned noise N from the noisy input data Y;

wherein parameters θ and θ′ of the neural network are optimized as follows for all i ∈ {1, . . . , M}:

θ

*

,

θ

′

*

=

arg

⁢

min

⁢

1

M

⁢

∑

i

=

1

M

Loss

(

n

⁡

(

i

)

,

g

θ

′

(

f

θ

(

y

⁡

(

i

)

)

)

)

where Loss is a loss function, n is a realization vector of the noise N, y is a realization vector of the noisy input data Y, M is a number of training dataset, the parameter θ is {W,b}, W is a weight matrix for encoding, b is a bias vector for encoding, the parameter θ′ is {W,b}, W is a weight matrix for decoding, b′ is a bias vector for decoding, go is a decoding function of the decoder of the neural network, and ƒ θ is an encoding function of the encoder of the neural network.

2 . The method of claim 1 , further comprising training the neural network, wherein training the neural network comprises:

inputting noisy training data into an encoder of the neural network; and

outputting training noise from a decoder of the neural network.

3 . The method of claim 1 , wherein the noisy input data Y are subcarrier signals of an orthogonal frequency-division multiplexing (OFDM) scheme, the regenerated original data X are original subcarrier signals, and the method further comprises demodulating the original subcarrier signals.

4 . The method of claim 1 , wherein the noisy input data Y are estimated distances between a target node and reference nodes, and the method further comprises using the original data X to estimate a position of the target node.

5 . The method of claim 1 , wherein the noisy input data Y are a corrupted image, the noise N is corruptions in the corrupted image, and the original data X is an original image.

6 . The method of claim 1 , wherein ƒ θ (y)=S(Wy+b), g θ′ (ƒ θ (y))=S(W′(ƒ θ (y))+b′), and S is a sigmoid activation function for neural networks.

7 . The method of claim 1 , wherein

x

~

n

⁢

l

(

j

)

is a j-th regenerated original data and is represented as follows for all j ∈ {1, . . . , L}:

x

~

n

⁢

l

(

j

)

=

y

(

j

)

-

n

~

(

j

)

=

y

(

j

)

-

g

θ

′

*

(

f

θ

*

(

y

(

j

)

)

)

,

where L is a number of test dataset.

8 . The method of claim 1 , wherein the neural network of the nlDAE comprises an input layer, an output layer, and one or more hidden layers connecting the input and output layers.

9 . A denoising method comprising:

determining whether to use a noise learning-based denoising autoencoder (nlDAE) method or a denoising autoencoder (DAE) method that learns an original data X directly, wherein determining whether to use the nlDAE method or the DAE method is based on one or more of (i) a ratio between a standard deviation of a noise N and a standard deviation of the original data X, (ii) mutual information between the original data X and a noisy input data Y, and (iii) mutual information between the noise N and the noisy input data Y; and

in response to determining to use the nlDAE method:

inputting noisy input data Y into an encoder of a neural network of a nlDAE;

using the neural network of the nlDAE to learn noise N in the noisy input data Y;

outputting the learned noise N from a decoder of the neural network of the nlDAE; and

using a subtractor of the nlDAE to regenerate original data X by subtracting the learned noise N from the noisy input data Y.

10 . The method of claim 9 , wherein parameters θ and θ′ of the neural network are optimized as follows for all i ∈ {1, . . . , M}:

θ

*

,

θ

′

*

=

arg

⁢

min

⁢

1

M

⁢

∑

i

=

1

M

Loss

(

n

⁡

(

i

)

,

g

θ

′

(

f

θ

(

y

⁡

(

i

)

)

)

)

where Loss is a loss function, n is a realization vector of the noise N, y is a realization vector of the noisy input data Y, M is a number of training dataset, the parameter θ is {W,b}, W is a weight matrix for encoding, b is a bias vector for encoding, the parameter θ′ is {W′,b′}, W′ is a weight matrix for decoding, b′ is a bias vector for decoding, g θ′ is a decoding function of the decoder of the neural network, and ƒ θ is an encoding function of the encoder of the neural network.

11 . The method of claim 10 , wherein ƒ θ (y)=S(Wy+b), g θ′ (ƒ θ (y))=S(W′(ƒ θ (y))+b′), and S is a sigmoid activation function for neural networks.

12 . The method of claim 10 , wherein

x

~

n

⁢

l

(

j

)

is j-th regenerated original data and is represented as follows for all j ∈ {1, . . . , L}:

x

~

n

⁢

l

(

j

)

=

y

(

j

)

-

n

~

(

j

)

=

y

(

j

)

-

g

θ

′

*

(

f

θ

*

(

y

(

j

)

)

)

,

where L is a number of test dataset.

13 . The method of claim 9 , wherein determining whether to use the nlDAE method or the DAE method is based on at least the ratio between the standard deviation of the noise N and the standard deviation of the original data X.

14 . The method of claim 9 , wherein determining whether to use the nlDAE method or the DAE method is based on at least the mutual information between the original data X and the noisy input data Y.

15 . The method of claim 9 , wherein determining whether to use the nlDAE method or the DAE method is based on at least the mutual information between the noise N and the noisy input data Y.

16 . The method of claim 9 , wherein the neural network of the nlDAE comprises an input layer, an output layer, and one or more hidden layers connecting the input and output layers.

17 . A noise learning-based denoising autoencoder (nlDAE) comprising:

a neural network including an encoder and a decoder, wherein the neural network is configured to receive noisy input data Y at inputs to the encoder, learn noise N in the noisy input data Y, and output the learned noise D from the decoder; and

a subtractor configured to regenerate original data X by subtracting the learned noise N from the noisy input data Y;

wherein parameters θ and θ′ of the neural network are optimized as follows for all i ∈ {1, . . . , M}:

θ

*

,

θ

′

*

=

arg

⁢

min

⁢

1

M

⁢

∑

i

=

1

M

Loss

(

n

⁡

(

i

)

,

g

θ

′

(

f

θ

(

y

⁡

(

i

)

)

)

)

where Loss is a loss function, n is a realization vector of the noise N, y is a realization vector of the noisy input data Y, M is a number of training dataset, the parameter θ is {W,b}, W is a weight matrix for encoding, b is a bias vector for encoding, the parameter θ′ is {W′,b′}, W′ is a weight matrix for decoding, b′ is a bias vector for decoding, g θ′ is a decoding function of the decoder of the neural network, and ƒ θ is an encoding function of the encoder of the neural network.

18 . The nlDAE of claim 17 , wherein ƒ θ (y)=S(Wy+b), g θ′ (ƒ θ (y))=S(W′(ƒ θ (y))+b′), and S is a sigmoid activation function for neural networks.

19 . The nlDAE of claim 17 , wherein

x

~

n

⁢

l

(

j

)

is a j-th regenerated original data and is represented as follows for all j ∈ {1, . . . , L}:

x

~

n

⁢

l

(

j

)

=

y

(

j

)

-

n

~

(

j

)

=

y

(

j

)

-

g

θ

′

*

(

f

θ

*

(

y

(

j

)

)

)

,

where L is a number of test dataset.

20 . The nlDAE of claim 17 , wherein the neural network of the nlDAE comprises an input layer, an output layer, and one or more hidden layers connecting the input and output layers.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 9, 2023
From: LEE, WOONGHEE; CHALLITA, URSULA; LI, JINGYA
To: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
Reel/Frame 063910/0901 →
Continuity (2)
Provisional Application 63088560 · Oct 7, 2020
Related Publication 20240095499A1 · Mar 21, 2024
References Cited (12)
US 10291268B1 · Migliori · 2019 [cited by examiner]
US 20180314985A1 · O'Shea · 2018 [cited by examiner]
US 20190096038A1 · El-Khamy et al. · 2019 [cited by applicant]
US 20200034948A1 · Park · 2020 [cited by examiner]
CN 107590778A · 2018 [cited by applicant]
Lin, Ju, et al. “Speech enhancement using forked generative adversarial networks with spectral subtraction.” Proceedings of Interspeech 2019 (2019). (Year: 2019). [cited by examiner]
I. Dokmanic, R. Parhizkar, J. Ranieri and M. Vetterli, “Euclidean Distance Matrices: Essential theory, algorithms, and applications,” in IEEE Signal Processing Magazine, vol. 32, No. 6, pp. 12-30, Nov. 2015 (Year: 2015). [cited by examiner]
International Search Report and Written Opinion issued in International Application No. PCT/EP2021/077326, dated Apr. 7, 2022 (19 pages). [cited by applicant]
Lin, Ju et al., “Speech Enhancement Using Forked Generative Adversarial Networks with Spectral Subtraction” INTERSPEECH 2019, Sep. 15, 2019 (Sep. 15, 2019), pp. 3163-3167, XP055882288. [cited by applicant]
Yang, Liuqing et al., “Random Noise Attenuation Based on Residual Convolutional Neural Network in Seismic Datasets”, IEEE Access, IEEE, USA, vol. 8, Feb. 7, 2020 (Feb. 7, 2020), pp. 30271-30286, XP011773288. [cited by applicant]
Ma, Yinjin et al., “Low-Dose CT Image Denoising Using a Generative Adversarial Network With a Hybrid Loss Function for Noise Learning”, IEEE Access, IEEE, USA, vol. 8, Apr. 7, 2020 (Apr. 7, 2020), pp. 67519-67529, XP011… [cited by applicant]
Barazideh, Reza et al., “Impulsive Noise Detection in OFDM-based Systems: A Deep Learning Perspective”, 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), IEEE, Jan. 7, 2019 (Jan. 7, 2019),… [cited by applicant]