GN Hearing A/S

An echo suppressor (10) for use in two-way voice communication through a communication network (4) in a scenario wherein near-end speech (SN) from a local user (1) is picked up by a microphone (8) for transmission to a remote participant (6) and far-end speech (RX) received from the remote participant (6) is reproduced for the local user (1) by a loudspeaker (7).The echo suppressor comprises:- a reference input (11) for receiving a first reference signal (R1) representative of far-end speech (RX) from the communication network (4);- a microphone input (12) for receiving a first microphone signal (M1) from the microphone (8) comprising a near-end speech portion representative of near-end speech (SN) from the local user (1) and an echo portion representative of direct and/or indirect acoustic feedback (SE) of far-end speech (SF) from the loudspeaker (7) to the microphone (8);- a first double-talk detector (13) configured to estimate a first double-talk likelihood (L1) being a likelihood of simultaneous presence of near-end speech and far-end speech in the first microphone signal (M1) and to provide a first double-talk signal (D1) indicating the first double-talk likelihood (L1);- a first echo reduction block (14) connected to receive a second reference signal (R2) equal to or derived from the first reference signal (R1), a second microphone signal (M2) equal to or derived from the first microphone signal (M1), and the first double-talk signal (D1), wherein the first echo reduction block (14) is configured to adaptively process the second microphone signal (M2) based on the second reference signal (R2) to estimate a first echo-cancelled signal (C1), and wherein the first echo reduction block (14) is further configured to control the processing of the second microphone signal (M2) in dependence on the first double-talk likelihood (L1); and- a near-end speech output (15) connected to receive a first echo-suppressed signal (S1) equal to or derived from the first echo-cancelled signal (C1), wherein the near-end speech output (15) is configured to provide a near-end speech signal (TX) comprising near-end speech for transmission to the communication network (4) based on the first echo-suppressed signal (S1).The echo suppressor (10) is characterized in that:- the echo suppressor (10) is configured to estimate a third microphone signal (M3) based on the first microphone signal (M1) and the first reference signal (R1); and- the first double-talk detector (13) is connected to receive the third microphone signal (M3) and is further configured to estimate the first double-talk likelihood (L1) in dependence on the first reference signal (R1) and the third microphone signal (M3).By estimating the double-talk likelihood (L1) in dependence on the third microphone signal (M3) wherein, preferably, the echo portion is reduced relative to the near-end speech portion when compared with the first microphone signal (M1), the first double-talk detector (13) may estimate the first double-talk likelihood (L1) with better accuracy and/or reliability and thereby enable the first echo reduction block (14) and the echo suppressor (10) to further reduce the echo portion relative to the near-end speech portion in the near-end speech signal (TX).

A video conference system (1), device, and method are disclosed. The device comprises a memory (18), an interface (20), and one or more processors (16). The one or more processors comprise a first neural network (20) configured to operate according to a first machine learning model. The one or more processors are configured to obtain audio data (24). The one or more processors are configured to process, using the first neural network, the audio data for provision of a first model output comprising a direction of arrival estimation. The one or more processors are configured to obtain camera data (25). The one or more processors are configured to process the camera data for provision of a video output. The one or more processors are configured to determine an uncertainty parameter based on the first model output and control the processing of the camera data for provision of the video output based on the uncertainty parameter.

Disclosed is a hearing device (100) comprising a charging receiver circuit (110) configured for converting an electromagnetic signal into a direct current, DC, signal. The charging receiver circuit (110) comprises a receiver coil circuit (120) configured to receive the electromagnetic signal from a power transmitter (220) and to generate an alternating current, AC, signal having a peak amplitude in response to the received electromagnetic signal, and a rectifier circuit (130) arranged in connection with the receiver coil circuit (120), wherein the rectifier circuit (130) is configured to receive the generated AC signal and to output the DC signal having a magnitude being above the peak amplitude of the generated AC signal.

An audio system (1) comprising an audio device (10) and a charging cradle (20) for storing the audio device (10). The charging cradle (20) comprises a cradle housing (200) with a device bay (201), a status detector (202), a cradle input interface (203), a rechargeable battery (204), and a cradle controller (205). The device bay (201) is configured to accommodate the audio device (10) when the audio device (10) is stored in the charging cradle (20). The status detector (202) is configured to detect whether the audio device (10) is stored in the charging cradle (20), determine a corresponding storing status, and provide the determined storing status in a cradle status signal (CS) to the cradle controller (205). The cradle input interface (203) is configured to detect user input actions and provide indications of detected user input actions in a cradle input signal (UC) to the cradle controller (205). The rechargeable battery (204) is configured to receive electric energy from an external energy source, store the received electrical energy, and provide stored electric energy (P) to the audio device (10) through the cradle controller (205) and/or the device bay (201). In the audio system (1), the cradle controller (205) is configured to provide a user output signal (UO) comprising an indication of control commands in response to receiving indications of detected user input actions in the cradle input signal (UC) and/or in dependence on the cradle status signal (CS), such that, for identical indicated user input actions, the control command indication in the user output signal (UO) differs for different storing status indications in the cradle status signal (CS). This enables using the controls of the cradle input interface (203) for different purposes, depending on whether the audio device (10) is stored in the charging cradle (20), and may thereby reduce the number of user controls required on the audio device (10) and/or the charging cradle (20).

The present invention relates to an audio device with a housing, a microphone arm and a detector for determining an orientation of the microphone arm relative to the housing. The invention may advantageously be applied in audio devices having a microphone arm, such as headsets, earphones, hearing protectors and other audio devices used for sound pickup. The audio device (1) comprises a housing (2), a microphone arm (3) that is mechanically and movably connected to the housing (2), a microphone unit (4) arranged at or in the microphone arm (3) and configured to pick up sound (5) from the environment of the audio device (1) and provide a corresponding microphone audio signal (M), a signal processor (5) arranged at or in the housing (2) and configured to provide electric power (P) to the microphone unit (4), and a flexible substrate (6) extending in a length direction (L) between a first end (7) mechanically connected to the housing (2) and a second opposite end (8) mechanically connected to the microphone arm (3). The flexible substrate (6) is configured to bend in dependence on the microphone arm (3) moving relative to the housing (2) and comprises one or more electrical conductors (9) electrically connecting the microphone unit (4) and the signal processor (5) to convey the electric power (P) from the signal processor (5) to the microphone unit (4) and/or the microphone audio signal (M) from the microphone unit (4) to the signal processor (5). The flexible substrate (6) further comprises a bend sensor (10) that is configured to change the value of an electric property in dependence on a bending of a first portion (11) of the flexible substrate (6), and the audio device (1) further comprises a bend detector (12) electrically connected to the bend sensor (10) and configured to estimate an orientation (O) of the microphone arm (3) relative to the housing (2) in dependence on the value of the electric property of the bend sensor (10). Arranging the bend sensor (10) at or in the flexible substrate (6) may provide a both reliable and cost-effective estimation of the orientation (O) of the microphone arm (43).

A method of head-tracking of a subject in a hearing system comprising a first hearing device and a second hearing device is disclosed. The method comprises obtaining, from a first accelerometer of the first hearing device, first accelerometer data. The method comprises obtaining, from a second accelerometer of the second hearing device, second accelerometer data. The method comprises determining a head parameter indicative of position and/or movement of the head of the subject based on the first accelerometer data and the second accelerometer data. The method comprises providing an output indicative of the head parameter.

Disclosed is a hearing device. The hearing device comprises a telecoil for communication in a first frequency band; a wireless communication device for communication in a second frequency band; and a printed circuit board, (PCB), comprising at least one conductive layer and at least one dielectric layer. The telecoil is arranged in a first section of the PCB and the wireless communication device is arranged in a second section of the PCB. The conductive layer comprises a first conductive trace provided in the first section of the PCB and a second conductive trace provided in the second section of the PCB. Further disclosed is a method of manufacturing a hearing device

A hearing device and related methods are disclosed, the hearing device comprising an interface and one or more processors, the one or more processors comprising a first primary machine learning model and a first secondary machine learning model, the first primary machine learning model for provision of a first primary model output based on a first primary model input, the first secondary machine learning model for provision of a first secondary model output based on a first secondary model input, wherein the first secondary model input is based on the first primary model output.

A hearing system and related methods are disclosed, the hearing system comprising a hearing device and an accessory device, the hearing device comprising a first interface and one or more processors comprising a first primary machine learning model for provision of a first primary model output based on a first primary model input, the accessory device comprising a second interface and one or more processors comprising a second machine learning model for provision of a second model output based on a second model input, wherein the accessory device is configured to transmit, via the second interface, a first accessory device output based on the second model output, and wherein the hearing device is configured to receive, via the first interface, the first accessory device output, and wherein the first primary model input is based on the first accessory device output.

A computer-implemented method (300) for continuously assessing a hearing device setting used in a hearing device (102) is disclosed. The hearing device (102) comprises a housing (104), a control circuitry (800) comprising a processing unit (802) and a memory (804), a first and a second microphone (806, 808), and a speaker (810). The method (300) comprises capturing (302) a first input signal using the first microphone (806), generating (306) first sound processor audio data by processing the first input signal using a first sound processor (820), , generating (314) second sound processor audio data by processing the first input signal using a second sound processor (822), and determining (316) whether the first sound processor audio data or the second sound processor audio data performs better based on a comparison of an objective measure.