公开(公告)号：US12073847B2

公开(公告)日：2024-08-27

申请号：US17827424

申请日：2022-05-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Amin Fazeli ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G10L21/0232 ,  G06N3/08 ,  G06N20/10 ,  G10L21/0208 ,  H04R3/04

CPC classification number: G10L21/0232 ,  G06N3/08 ,  G06N20/10 ,  H04R3/04 ,  G10L2021/02082

Abstract: A system for performing echo cancellation includes: a processor configured to: receive a far-end signal; record a microphone signal including: a near-end signal; and an echo signal corresponding to the far-end signal; extract far-end features from the far-end signal; extract microphone features from the microphone signal; compute estimated near-end features by supplying the microphone features and the far-end features to an acoustic echo cancellation module including a recurrent neural network including: an encoder including a plurality of gated recurrent units; and a decoder including a plurality of gated recurrent units; compute an estimated near-end signal from the estimated near-end features; and transmit the estimated near-end signal to the far-end device. The recurrent neural network may include a contextual attention module; and the recurrent neural network may take, as input, a plurality of error features computed based on the far-end features, the microphone features, and acoustic path parameters.

公开(公告)号：US12051237B2

公开(公告)日：2024-07-30

申请号：US17674832

申请日：2022-02-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Behnam Babagholami Mohamadabadi ,  Qingfeng Liu ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06V10/82 ,  G06N5/04 ,  G06V10/774 ,  G06V10/776 ,  G06V10/778

CPC classification number: G06V10/82 ,  G06N5/04 ,  G06V10/774 ,  G06V10/776 ,  G06V10/7784

Abstract: A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.

公开(公告)号：US11900234B2

公开(公告)日：2024-02-13

申请号：US17007739

申请日：2020-08-31

Applicant: Samsung Electronics Co., Ltd.

Inventor： Haoyu Ren ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: G06N20/00 ,  G06N3/04 ,  G06N3/08 ,  G06N3/082 ,  G06N3/045

CPC classification number: G06N3/04 ,  G06N3/045 ,  G06N3/08 ,  G06N3/082 ,  G06N20/00

Abstract: Apparatuses and methods of manufacturing same, systems, and methods for generating a convolutional neural network (CNN) are described. In one aspect, a minimal CNN having, e.g., three or more layers is trained. Cascade training may be performed on the trained CNN to insert one or more intermediate layers until a training error is less than a threshold. When cascade training is complete, cascade network trimming of the CNN output from the cascade training may be performed to improve computational efficiency. To further reduce network parameters, convolutional filters may be replaced with dilated convolutional filters with the same receptive field, followed by additional training/fine-tuning.

公开(公告)号：US11847826B2

公开(公告)日：2023-12-19

申请号：US18083081

申请日：2022-12-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Qingfeng Liu ,  Mostafa El-Khamy ,  Rama Mythili Vadali ,  Tae-ui Kim ,  Andrea Kang ,  Dongwoon Bai ,  Jungwon Lee ,  Maiyuran Wijay ,  Jaewon Yoo

IPC: G06T7/00 ,  G06V20/00 ,  G06V20/10 ,  G06F18/24 ,  H04N23/61 ,  H04N23/667 ,  G06V10/764 ,  G06V10/82 ,  G06V10/26 ,  G06V10/50

CPC classification number: G06V20/35 ,  G06F18/24 ,  G06V10/26 ,  G06V10/50 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  H04N23/61 ,  H04N23/667

Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.

公开(公告)号：US11699070B2

公开(公告)日：2023-07-11

申请号：US16452005

申请日：2019-06-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Jungwon Lee ,  Yoo Jin Choi ,  Haoyu Ren

IPC: G06N3/08 ,  G06N20/10 ,  G06F18/214 ,  G06V10/82 ,  G06V10/44 ,  G06V10/46

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06N20/10 ,  G06V10/454 ,  G06V10/462 ,  G06V10/82

Abstract: A method and apparatus for providing a rotational invariant neural network is herein disclosed. According to one embodiment, a method includes receiving a first input of an image in a first orientation and training a kernel to be symmetric such that an output corresponding to the first input is the same as an output corresponding to a second input of the image in a second orientation.

公开(公告)号：US11687780B2

公开(公告)日：2023-06-27

申请号：US17241848

申请日：2021-04-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Qingfeng Liu ,  Mostafa El-Khamy ,  Jungwon Lee ,  Behnam Babagholami Mohamadabadi

IPC: G06K9/62 ,  G06N3/08 ,  G06F18/2323 ,  G06F18/2415 ,  G06F18/2431 ,  G06V30/19 ,  G06V10/772 ,  G06V10/774 ,  G06V10/80 ,  G06F18/2321 ,  G06F18/25 ,  G06N3/045 ,  G06N3/04 ,  G06N5/022 ,  G06N5/025

CPC classification number: G06N3/08 ,  G06F18/2321 ,  G06F18/2323 ,  G06F18/2415 ,  G06F18/2431 ,  G06F18/253 ,  G06F18/254 ,  G06N3/04 ,  G06N3/045 ,  G06N5/022 ,  G06N5/025 ,  G06V10/772 ,  G06V10/774 ,  G06V10/806 ,  G06V10/809 ,  G06V30/1914 ,  G06V30/1918 ,  G06V30/19107 ,  G06V30/19147

Abstract: A method and system for training a neural network are provided. The method includes receiving an input image, selecting at least one data augmentation method from a pool of data augmentation methods, generating an augmented image by applying the selected at least one data augmentation method to the input image, and generating a mixed image from the input image and the augmented image.

公开(公告)号：US11615317B2

公开(公告)日：2023-03-28

申请号：US16886429

申请日：2020-05-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin Choi ,  Jongha Ryu ,  Mostafa El-Khamy ,  Jungwon Lee ,  Young-Han Kim

IPC: G06N20/20 ,  G06N3/088 ,  G06N3/04

Abstract: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

公开(公告)号：US20230006692A1

公开(公告)日：2023-01-05

申请号：US17941318

申请日：2022-09-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yoo Jin CHOI ,  Mostafa El-Khamy ,  Jungwon Lee

IPC: H03M7/30 ,  H04N19/13 ,  H04N19/147 ,  G06N3/08 ,  H04L1/00 ,  G06N3/04 ,  H04N19/19

Abstract: A method and apparatus for variable rate compression with a conditional autoencoder is herein provided. According to one embodiment, a method for compression includes receiving a first image and a first scheme as inputs for an autoencoder network; determining a first Lagrange multiplier based on the first scheme; and using the first image and the first Lagrange multiplier as inputs, computing a second image from the autoencoder network. The autoencoder network is trained using a plurality of Lagrange multipliers and a second image as training inputs.

公开(公告)号：US11532154B2

公开(公告)日：2022-12-20

申请号：US17177720

申请日：2021-02-17

Applicant: Samsung Electronics Co., Ltd.

Inventor： Qingfeng Liu ,  Mostafa El-Khamy ,  Rama Mythili Vadali ,  Tae-ui Kim ,  Andrea Kang ,  Dongwoon Bai ,  Jungwon Lee ,  Maiyuran Wijay ,  Jaewon Yoo

IPC: G06K9/62 ,  G06V20/10 ,  H04N5/232 ,  G06V10/50

Abstract: A method for computing a dominant class of a scene includes: receiving an input image of a scene; generating a segmentation map of the input image, the segmentation map being labeled with a plurality of corresponding classes of a plurality of classes; computing a plurality of area ratios based on the segmentation map, each of the area ratios corresponding to a different class of the plurality of classes of the segmentation map; and outputting a detected dominant class of the scene based on a plurality of ranked labels based on the area ratios.

公开(公告)号：US11526970B2

公开(公告)日：2022-12-13

申请号：US16842386

申请日：2020-04-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Mostafa El-Khamy ,  Ryan Szeto ,  Jungwon Lee

IPC: G06K9/00 ,  G06T5/50 ,  H04N7/01 ,  G06T3/00 ,  G06T5/00

Abstract: A system and method for processing an input video while maintaining temporal consistency across video frames is provided. The method includes converting the input video from a first frame rate to a second frame rate, wherein the second frame rate is a faster frame rate than the first frame rate; generating processed frames of the input video at the second frame rate; and aggregating the processed frames using temporal sliding window aggregation to yield a processed output video at a third frame rate.