公开(公告)号：US20240073608A1

公开(公告)日：2024-02-29

申请号：US18455826

申请日：2023-08-25

Applicant: GN Audio A/S

Inventor： Karim HADDAD ,  Clément LAROCHE ,  Rasmus Kongsgaard OLSSON

IPC: H04R5/04 ,  H04M3/42 ,  H04M3/56 ,  H04R3/00

CPC classification number: H04R5/04 ,  H04M3/42229 ,  H04M3/56 ,  H04R3/005 ,  H04R2203/12

Abstract: A speakerphone is disclosed. The speakerphone comprises an interface, a speaker, a plurality of microphones, a processor, and a memory. The speakerphone is configured to: obtain a first plurality of microphone input signals of a conference; determine a first plurality of beamforming parameters; obtain a first internal output signal for provision of a first internal audio output signal; output the first internal audio output signal; obtain a third microphone input signal associated with the first internal audio output signal; obtain a second internal output signal for provision of a second internal audio output signal; output the second internal audio output signal; obtain a fourth microphone input signal associated with the second internal audio output signal; determine a first impulse response; determine a second impulse response; and determine one or more conference parameters indicative of a conference configuration, the one or more conference parameters including a first conference parameter; and output the first conference parameter.

公开(公告)号：US20240276171A1

公开(公告)日：2024-08-15

申请号：US18433868

申请日：2024-02-06

Applicant: GN Audio A/S

Inventor： Pejman MOWLAEE ,  Rasmus Kongsgaard OLSSON ,  Karim HADDAD

IPC: H04S7/00

CPC classification number: H04S7/305 ,  H04S7/301 ,  H04S2400/09

Abstract: A computer-implemented method for processing audio input data into processed audio data by using an audio device comprising a microphone, a processor device and a memory holding a plurality of neural networks is presented. The plurality of neural networks are associated with different room types, wherein each room type is associated with one or more reference room acoustic metrics. The method comprises obtaining, by the microphone, room response data, wherein the room response data is reflecting room acoustics of a room in which the audio device is placed, determining, by using the processor device, the one or more room acoustic metrics based on the room response data, and selecting, by using the processor device, a matching neural network among the plurality of neural networks by comparing the one or more room acoustic metrics with the one or more reference room acoustic metrics associated with the different room types associated with the plurality of neural networks.

公开(公告)号：US20240064241A1

公开(公告)日：2024-02-22

申请号：US18232389

申请日：2023-08-10

Applicant: GN Audio A/S

Inventor： Karim HADDAD ,  Clément LAROCHE ,  Rasmus Kongsgaard OLSSON

IPC: H04M9/08 ,  G10L25/84

CPC classification number: H04M9/082 ,  G10L25/84

Abstract: A speakerphone is disclosed. The speakerphone comprises an interface, a speaker, one or more microphones including a first microphone, a processor, and a memory. The speakerphone is configured to obtain an internal output signal for provision of an internal audio output signal in an environment. The speakerphone is configured to output the internal audio output signal in the environment. The speakerphone is configured to obtain a microphone input signal. The speakerphone is configured to determine an impulse response associated with the environment. The speakerphone is configured to determine one or more environment parameters indicative of acoustics of the environment. The speakerphone is configured to transmit the impulse response and/or the first environment parameter to a server device.

公开(公告)号：US20240212668A1

公开(公告)日：2024-06-27

申请号：US18542728

申请日：2023-12-17

Applicant: GN Audio A/S

Inventor： Karim HADDAD ,  Pejman MOWLAEE ,  Rasmus Kongsgaard OLSSON

IPC: G10L15/06 ,  G10L21/0208 ,  G10L21/0216 ,  G10L25/30 ,  G10L25/60

CPC classification number: G10L15/063 ,  G10L21/0216 ,  G10L25/30 ,  G10L25/60 ,  G10L2021/02082

Abstract: A computer-implemented method (600) for training a neural network (100) by using a data processing device (102) is presented. The method (600) comprises providing (602) pairs (110) of target audio data sets (106) and distorted audio data sets (108) to the neural network (100), providing (604) values (112) of user preference settings, wherein the values (112) are associated to the pairs (110) of target and distorted audio data sets (106, 108), such that the neural network (100) can be trained by a combination of the pairs (110) of the target audio data (106) and the distorted audio data (108) in combination with the values (112) of the user preference settings, wherein the distorted audio data (108) and the values (112) of the user preference settings are used as inputs to the neural network (100) during training, and wherein a loss function (114) used for training the neural network is a function of the values (112) of the user preference settings, the target audio data (106), and the distorted audio data (108) thereby providing for that a variety of user preference settings can be met with one and the same trained neural network.

公开(公告)号：US20240064229A1

公开(公告)日：2024-02-22

申请号：US18232841

申请日：2023-08-11

Applicant: GN Audio A/S

Inventor： Karim HADDAD ,  Clément LAROCHE ,  Rasmus Kongsgaard OLSSON

IPC: H04M3/00

CPC classification number: H04M3/002

Abstract: A speakerphone is disclosed. The speakerphone comprises an interface, a speaker, one or more microphones including a first microphone, a processor, and a memory. The speakerphone is configured to obtain an internal output signal for provision of an internal audio output signal in an environment. The speakerphone is configured to output the internal audio output signal in the environment. The speakerphone is configured to obtain a microphone input signal. The speakerphone is configured to determine an impulse response associated with the environment. The speakerphone is configured to determine one or more environment parameters indicative of acoustics of the environment. The speakerphone is configured to determine an environment score indicative of suitability of a conference setup in the environment. The speakerphone is configured to output the environment score.