公开(公告)号：US20220330036A1

公开(公告)日：2022-10-13

申请号：US17707448

申请日：2022-03-29

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Faycal AIT AOUDIA ,  Jakob HOYDIS ,  Dani Johannes KORPI ,  Janne Matti Juhani HUTTUNEN ,  Mikko Johannes HONKALA

IPC: H04W16/22 ,  G06N3/04 ,  H04W72/04

Abstract: Disclosed is a method comprising providing a first resource grid as input to a first machine learning algorithm, obtaining a second resource grid as output from the first machine learning algorithm, and transmitting a signal comprising the second resource grid by using orthogonal frequency-division multiplexing modulation.

公开(公告)号：US20240333457A1

公开(公告)日：2024-10-03

申请号：US18618548

申请日：2024-03-27

Applicant: Nokia Technologies Oy

Inventor： Dani Johannes KORPI ,  Mikko Johannes HONKALA ,  Janne Matti Juhani HUTTUNEN ,  Antti Anton TOSKALA

IPC: H04L5/00

CPC classification number: H04L5/0051

Abstract: Examples of the disclosure relate to apparatus, methods and computer programs for transmitting data. In examples of the disclosure a User Equipment (UE) can receive a configuration for releasing demodulation reference signal (DMRS) resources for uplink transmission. The releasing of the DMRS resources is contingent upon a resource allocation for the uplink transmission satisfying one or more criteria. The UE can also receive a resource allocation for the uplink transmission. If the resource allocation satisfies the one or more criteria the UE can release at least some of the DMRS resources. The UE can then use at least some of the released DMRS resources as a data resource within the resource allocation and transmit data using at least some of the released DMRS resources.

公开(公告)号：US20240073933A1

公开(公告)日：2024-02-29

申请号：US18355371

申请日：2023-07-19

Applicant: NOKIA TECHNOLOGIES OY

Inventor： Janne Matti Juhani HUTTUNEN ,  Dani Johannes KORPI ,  Mikko Johannes HONKALA ,  Mikko Aleksi UUSITALO

IPC: H04W72/40 ,  H04L5/00 ,  H04W72/04

CPC classification number: H04W72/40 ,  H04L5/0094 ,  H04W72/04

Abstract: According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core and at least one memory storing instructions that, when executed by the at least one processing core, cause the apparatus at least to transmit in uplink or sidelink, or receive in downlink, using orthogonal frequency-division multiplexing, via a physical shared channel in a system comprising resource block groups, each resource block group comprising two or more resource blocks, each resource block comprising plural subcarriers which are consecutive to each other in frequency, and process an allocation of resources for the physical shared channel, the allocation received from a network node, the allocation defining that the apparatus may use a part of, but not all, subcarriers of each one of one or more resource blocks for communication via the physical shared channel.

公开(公告)号：US20230308317A1

公开(公告)日：2023-09-28

申请号：US18021631

申请日：2020-08-20

Applicant: Nokia Technologies Oy

Inventor： Dani Johannes Korpi ,  Mikko Aleksi UUSITALO ,  Janne Matti Juhani HUTTUNEN ,  Leo Mikko Johannes KARKKAINEN ,  Mikko Johannes HONKALA

IPC: H04L25/03 ,  H04B1/10

CPC classification number: H04L25/03165 ,  H04B1/10

Abstract: In some examples, a node for a telecommunication network includes a neural-network-based receiver for uplink communications. The node is configured to modify the neural-network-based receiver to generate a set of modified receiver frameworks defining respective different versions for the receiver, using each of the modified receiver frameworks, generate respective measures representing bits encoded by a signal received at the node, calculate a value representing a variance of the measures, and on the basis of the value, determine whether to select the signal received at the node for use as part of a training set of data for the neural-network-based receiver.

公开(公告)号：US20250119335A1

公开(公告)日：2025-04-10

申请号：US18729416

申请日：2022-01-19

Applicant: Nokia Technologies Oy

Inventor： Dani Johannes KORPI ,  Mikko Johannes HONKALA ,  Janne Matti Juhani HUTTUNEN ,  Mikko Aleksi UUSITALO

IPC: H04L27/34

Abstract: Disclosed is a method comprising transforming, by a terminal device, a signal constellation based on one or more parameter values, wherein the one or more parameter values indicate a shape of the transformed signal constellation; and transmitting, by the terminal device, one or more signals based at least partly on the transformed signal constellation.

公开(公告)号：US20240298133A1

公开(公告)日：2024-09-05

申请号：US18571326

申请日：2022-05-24

Applicant: Nokia Technologies Oy

Inventor： Juha Tapio Vilkamo ,  Mikko Johannes HONKALA

IPC: H04S7/00 ,  G06N3/08 ,  H04R3/00 ,  H04R5/027

CPC classification number: H04S7/302 ,  G06N3/08 ,  H04R3/005 ,  H04R5/027 ,  H04S2400/11 ,  H04S2400/15 ,  H04S2420/03 ,  H04S2420/07

Abstract: An apparatus includes circuitry for training a machine learning model such as a neural network to estimate spatial metadata for a spatial sound distribution. The apparatus includes circuitry for obtaining first capture data for a machine learning model where the first capture data is related to a plurality of spatial sound distributions and where the first capture data relates to a target device configured to obtain at least two microphone signals. The apparatus also includes circuitry for obtaining second capture data for the machine learning model where the second capture data is obtained using the same spatial sound distributions and where the data includes information indicative of spatial properties of the spatial sound distributions and the data is obtained using a reference capture method. The apparatus also includes circuitry for training the machine learning model to estimate the second capture data based on the first capture data.

公开(公告)号：US20240284134A1

公开(公告)日：2024-08-22

申请号：US18571311

申请日：2022-05-16

Applicant: Nokia Technologies Oy

Inventor： Juha Tapio VILKAMO ,  Mikko Johannes HONKALA

IPC: H04S7/00 ,  G10L19/008

CPC classification number: H04S7/302 ,  G10L19/008 ,  H04S2400/11 ,  H04S2400/15 ,  H04S2420/07

Abstract: Examples of the disclosure relate to obtaining spatial metadata for use in rendering, or otherwise processing spatial audio. In examples of the disclosure a machine learning model can be used to process microphone signals, or data obtained from microphone signals, to obtain the spatial metadata. The machine learning model can be trained to enable high quality spatial metadata to be obtained from sub-optimal or low-quality microphone arrays. Examples of the disclosure include an apparatus including circuitry for: accessing a trained machine learning model; determining input data for the machine learning model based on two or more microphone signals; enabling using the machine learning model to process the input data to obtain spatial metadata; and associating the obtained spatial metadata with at least one signal based on the two or more microphone signals to enable processing of the at least one signal based on the obtained spatial metadata.