Crowell & Moring U.K. LLP

An ear-wearable device includes at least two microphones arranged to provide separate directional information from ambient sound that has a speech component. A processor is configured to receive at least two audio signals from the respective at least two microphones. The at least two audio signals are mapped to an input layer of a deep neural network. The deep neural network is trained to estimate filter weights for an optimal directionality pattern which aims to extract the speech component from the ambient sound. The processor beamforms the at least two microphones to utilize the optimal directionality pattern.

Enhancing sound in an ear-wearable device involves receiving an ambient sound stream from a microphone of an ear-wearable device and inputting a representation of the ambient sound stream to a deep neural network that is trained to detect speech in a noisy environment. In response to detecting the speech via the deep neural network, the ear-wearable device operates in a directional mode in which an audio representation derived from the ambient sound stream is emphasized in a target direction. In response to detecting no speech via the deep neural network, the ear-wearable device operates in a spatial omnidirectional mode in which a fixed directional mode signal is combined with an omnidirectional signal to provide the audio representation. The fixed directional mode signal and the omnidirectional signal operate over different frequency ranges.

A system includes a hearing instrument and a vision device configured to be worn concurrently by a user. The hearing instrument receives an indication of a direction from the vision device. One or more processors of the hearing instrument receive first audio data representing sound detected by one or more microphones. The processors generate second audio data based on the first audio data, representing a version of the detected sound in which portions arriving from the indicated direction are enhanced. A receiver generates output sound based on the second audio data.

A control method and an apparatus for a power supply system, and a power supply system are provided. The control method includes: obtaining a current SOC and current charging/discharging power of the energy storage apparatus connected to the first power supply device; and executing a target control policy, in response to the current SOC exceeding a target SOC range, or the current charging/discharging power exceeding a target power range. The executing the target control policy includes: controlling a frequency of the first power supply device; or controlling a contactor connected to the second power supply device to be disconnected, to disconnect the second power supply device from the coupling point.

Some embodiments of the present disclosure relate to an additively manufactured transport structure. The transport structure includes cavities into which components that use an external interface are inserted. A plurality of components are assembled and integrated into the vehicle. In an embodiment, the components and frame are modular, enabling reparability and replacement of single parts in the event of isolated failures.

Self-learning hearing device may enhance audio input based on an adaptive model. The adaptive, or changeable, model may be updatable in response to, among other things, user settings adjustments. For example, when a user makes a settings adjustment, the context surrounding, or corresponding to, the settings adjustment may be used to update the adaptive model.

Embodiments herein relate to ear-worn devices magnetic rechargeable interfaces. In an embodiment, an ear-worn device system for listening includes having a first ear-worn device having a first ear-worn device charging structure having an ear-worn device alignment structure with a magnetic material; and a charger case having a first case charging structure and a case alignment structure, wherein the first case charging structure includes a first case electrical contact, wherein the case alignment structure includes a first pole-aligned magnet and a second pole-aligned magnet having opposite poles and positioned on a first side of the case alignment structure, wherein the magnetic material is magnetically attracted to the first pole-aligned magnet and the second pole-aligned magnet. Other embodiments are also included herein.

Zusammenfassung wird geladen …

There is provided a computer-implemented method for monitoring a food preparation process. The method comprises receiving an input identifying a composite food product to be prepared, the preparation of the composite food product comprising a plurality of prescribed processing steps. The method further comprises receiving visual data from an image sensor, the visual data tracking the preparation of the composite food product. The method further comprises identifying, for a first processing step of the plurality of processing steps, a first subset of the visual data that tracks the performance of that processing step. The method further comprises comparing the first subset of the visual data to a first baseline condition for the performance of the first processing step. The method further comprises determining, from the comparison, that a difference between the first subset of the visual data and the first baseline condition fails a predetermined threshold condition and generating a signal indicative that the food preparation process has been unsuccessful.

A system, a method, and a computer program product for providing wearable continuous blood glucose monitoring. In some embodiments, there is provided a method that includes receiving, at a smartwatch, an alert representative of a glucose state of a host-patient coupled to a glucose sensor; detecting, at the smartwatch, a predetermined action indicative of a request to generate a glance view providing an indication of the glucose state of the host-patient; and presenting, at the smartwatch and in response to the detecting, the glance view providing the indication of the glucose state of the host-patient.