-
公开(公告)号：US20230368071A1
公开(公告)日：2023-11-16
申请号：US18104002
申请日：2023-01-31
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Mehmet Kerim YUCEL , Mete OZAY , Albert SAA-GARRIGA , Bruno MANGANELLI
CPC classification number: G06N20/00 , G06T7/11 , G06T2207/20104 , G06T2207/20081
Abstract: A computer-implemented federated learning method is disclosed. The method comprises: for each of a number, n, of clients: determining a diversity score of a dataset corresponding to that client for training a machine learning model, wherein the diversity score is a measure of dataset variability; aggregating, weighted by the respective diversity score, models corresponding to each of the clients; and sending the aggregated model to at least one receiving client.
-
公开(公告)号：US20250006183A1
公开(公告)日：2025-01-02
申请号：US18587238
申请日：2024-02-26
Applicant: Samsung Electronics Co., Ltd.
Inventor： Pablo Peso PARADA , Mete OZAY , Karthikeyan SARAVANAN
Abstract: The disclosure generally relate to a method performed by a user device obtaining a pre-trained automatic speech recognition (ASR) model, obtaining a user data from a user database, analysing a distribution of the user data with respect to an acoustic characteristic, determining, using the distribution, whether data augmentation for the acoustic characteristic is to be applied, when it is determined that data augmentation is to be applied, dividing the user data into a training subset and a validation subset, based on an acoustic characteristic being less audible in the training subset than in the validation subset, applying data augmentation to add the acoustic characteristic to the user data in the training subset, and updating the pre-trained ASR model with the augmented training subset to generate a personalised local ML model.
-
公开(公告)号：US20240013775A1
公开(公告)日：2024-01-11
申请号：US18371233
申请日：2023-09-21
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Pablo PESO PARADA , Agnieszka DOBROWOLSKA , Karthikeyan SARAVANAN , Mete OZAY
IPC: G10L15/06 , G10L21/0216
CPC classification number: G10L15/063 , G10L21/0216
Abstract: A method of obtaining a patched signal for training a model for use in at least one of a speech and an audio recognition is disclosed. The method comprises obtaining a first signal, wherein the first signal is at least one of a speech and an audio signal, modifying the first signal to obtain at least one second signal, dividing the first signal and the at least one second signal respectively into a plurality of first patches and a plurality of second patches, wherein each one of the plurality of first patches comprises a respective part of the first signal and each one of the plurality of second patches comprises a respective part of the at least one second signal and mixing selected ones of the plurality of first patches and the plurality of second patches to obtain a patched signal.
-
公开(公告)号：US20240257800A1
公开(公告)日：2024-08-01
申请号：US18405666
申请日：2024-01-05
Applicant: Samsung Electronics Co., Ltd.
Inventor： Umberto MICHIELI , Mete OZAY , Edward FISH
CPC classification number: G10L15/063 , G10L15/30
Abstract: The present techniques generally relate to a computer-implemented method for personalising automatic speech recognition (ASR) or other general-purpose models using mixed precision (MP) quantization. Each model is personalised on a user device or server to a target memory budget B using user data.
-
公开(公告)号：US20240054395A1
公开(公告)日：2024-02-15
申请号：US18206859
申请日：2023-06-07
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Mete OZAY
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: Broadly speaking, embodiments of the present techniques provide a method and system for providing personal machine learning, ML, models. In particular, the present application provides a system for developing a training personal and personalised models to improve user experience.
-
Patent Agency Ranking
公开(公告)号：US20230145919A1
公开(公告)日：2023-05-11
申请号：US17984010
申请日：2022-11-09
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Mete OZAY , Marco Toldo
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: The present application generally relates to a method for training a machine learning, ML, model using class incremental learning, and to a computer-implemented method and apparatus for using the trained machine learning, ML, model. The method may learn how to update semantic representations of old concepts (classes) by modelling drift of semantic representations. The method may also learn how to update feature representations of old concepts (classes) by modelling drift of feature representations
-
公开(公告)号：US20250078495A1
公开(公告)日：2025-03-06
申请号：US18933406
申请日：2024-10-31
Applicant: Samsung Electronics Co., Ltd.
Inventor： Umberto MICHIELI , Mete OZAY , Jijoong MOON , Daehyun KIM , Elena CAMUFFO
IPC: G06V10/98 , G06V10/774 , G06V10/778 , G06V10/82
Abstract: The present disclosure relates to a computer-implemented method of performing a computer vision task. The computer-implemented method comprises: receiving a corrupted image from a camera; estimating a corruption type of the corrupted image using a corruption identification module; obtaining normalisation parameters associated with the estimated corruption type; updating a computer vision model, trained to perform the task, by replacing normalisation parameters of the computer vision model with the obtained normalisation parameters; and performing the task using the updated computer vision model.
-
公开(公告)号：US20240303883A1
公开(公告)日：2024-09-12
申请号：US18529533
申请日：2023-12-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Savas OZKAN , Mete OZAY , Tom ROBINSON
IPC: G06T11/60 , G06V10/774 , G06V10/778 , G06V10/94 , G06V40/16
CPC classification number: G06T11/60 , G06V10/774 , G06V10/7788 , G06V10/945 , G06V40/168 , G06V40/172
Abstract: Broadly speaking, the present techniques generally relate to a method for performing image processing using a machine learning, ML, model. In particular, the present application relates to a method for generating modified images from input images depicting human faces using a trained ML model. Advantageously, the present techniques enable manipulation of human faces within images in a way that allows one aspect of the image of the human face to be altered without impacting other aspects.
-
公开(公告)号：US20240289491A1
公开(公告)日：2024-08-29
申请号：US18629401
申请日：2024-04-08
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Jisi ZHANG , Md Asif JALAL , Karthikeyan SARAVANAN , Pablo PESO PARADA , Mete OZAY
IPC: G06F21/62 , G10L15/02 , G10L15/06 , G10L15/16 , G10L15/22 , G10L15/30 , G10L21/007 , G10L21/0208
CPC classification number: G06F21/6254 , G10L15/02 , G10L15/063 , G10L15/16 , G10L15/22 , G10L15/30 , G10L21/007 , G10L21/0208
Abstract: Broadly speaking, the present disclosure relates to a computer-implemented method for training a machine learning, ML, automatic speech recognition, ASR, model. The method comprises injecting a speaker anonymiser, which is configured to cause the ML ASR model to generate anonymised acoustic embeddings for the ML ASR model, at one or more layers of the ML ASR model, and suitably training the ML ASR model including the speaker anonymiser on audio data comprising an utterance with one or more words to be recognised. Correspondingly, there is also described a computer implemented method for performing automatic speech recognition using the trained ML ASR model and system for training/inference thereof.
-
公开(公告)号：US20230351203A1
公开(公告)日：2023-11-02
申请号：US18218405
申请日：2023-07-05
Applicant: SAMSUNG ELECTRONICS CO., LTD.
Inventor： Mete OZAY
Abstract: The present techniques generally relate to a system and method for knowledge distillation between machine learning, ML, models. In particular, the present application relates to a computer-implemented method for training a condenser model to learn how to transfer knowledge between a teacher model and a student model, and using this trained condenser model to more quickly generate new student models.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.03 seconds)
