Abstract: Provided is a technique for providing feedback on the degree of utterance volume to an utterer. The utterance feedback device includes: an utterance volume evaluation unit that generates an evaluation value for a volume of an utterance voice (referred to as utterance volume evaluation value, hereinafter) from a first sound collection signal that is output by a first microphone installed near an utterer to collect an utterance voice, which is a voice of the utterer, and a second sound collection signal that is output by a second microphone installed at a position farther away from the utterer than the first microphone to collect the utterance voice; and a feedback sound signal generation unit that generates a signal for emitting, from a speaker, a feedback sound indicating the degree of the volume of the utterance voice to the utterer (hereinafter referred to as a feedback sound signal), from the first sound collection signal, by using a feedback gain corresponding to the utterance volume evaluation value.

Abstract: The present invention aims to reduce power consumption in the operation based upon a recognition device (1000) including, in a neural network of multiple layers that output type of an object and existing coordinates based on external environment information, a selector (103) that selects input data to convolution operation units (107-1 to L) from external environment information; convolution operation units (107-1 to L) configured by a plurality of layers connected in cascade; and a parameter storage unit (109) that stores a weight parameter of each layer, a cumulative addition count of each layer, and an omitting bit number of each layer. The recognition device includes operation stop signal generation units (116-1 to L) that transmit one or more stop signals for stopping some or all of the computing units of the convolution operation units (107-1 to L) to the convolution operation units (107-1 to L) for each layer.

Abstract: A filter information determination device includes: a filter information storage unit configured to store multiple pieces of filter information for performing filter processing on a signal to be reproduced by a wearable device that reproduces a sound without completely blocking external ear canal; a filter processing unit configured to perform filter processing on a predetermined signal using filter information from the multiple pieces of filter information read from the filter information storage unit to generate a filtered signal; and a filter information selection unit configured to select filter information from the multiple pieces of filter information based on a localization evaluation of sound based on the filtered signal by a user who listens to the sound based on the filtered signal radiated by the wearable device.

Abstract: This image recognition device, which performs object detection by using an image recognition program with respect to an input image, comprises: a storage unit that stores a current program, which is a conventional image recognition program, and a new program, which is a new image recognition program; a difference extraction unit that extracts a detection difference which is a difference between an object detection result of the current program and an image recognition result of the new program with respect to the same input image; a transmission determination unit that determines a saving need as to whether or not to save the input image on the basis of a status of appearance of the detection difference; and a saving unit that outputs the input image that the transmission determination unit has determined to save to the outside of the image recognition device, or that saves the input image that the transmission determination unit has determined to save in the image recognition device.

Abstract: Provided is a playback sound correction apparatus that corrects a playback sound of an open-ear earphone including a speaker and a microphone, the apparatus including: a characteristics measuring sound playback unit configured to play back a characteristics measuring sound from the speaker; a transfer function calculation unit configured to calculate a transfer function from the speaker to the microphone based on a recorded sound of the microphone and the characteristics measuring sound; a correction filter calculation unit configured to calculate an inverse filter of the transfer function as a correction filter; and a playback sound correction unit configured to correct the playback sound with the correction filter.

Abstract: A gasket molding method for molding a gasket on a workpiece includes, in the stated order: an application step of applying an active energy ray curable liquid having a structural viscosity ratio of 1.5 or more and 4.0 or less into a cavity of a molding die; a bonding step of bonding the molding die coated with the active energy ray curable liquid and the workpiece to each other; a curing step of curing the applied active energy ray curable liquid by irradiation with an active energy ray; and a mold release step of pulling off the cured active energy ray curable liquid from the molding die together with the workpiece, in which the application step includes an overlapping region of application trajectories. Accordingly, there is provided a gasket molding method by which mixing of air bubbles in an overlapping region of application trajectories is suppressed.

Abstract: A noise suppression technique which operates stably even when a reference microphone or an error microphone picks up sound other than noise assumed to occur around a user is provided. A noise suppression device suppresses a noise suppression function for sounds other than noise expected to occur around the user.

Abstract: A display device includes a substrate including a first side and a second side adjoining the first side, a plurality of light emitters located on the substrate, a plurality of emission control signal lines located on the substrate to control an emission state or a non-emission state of the plurality of light emitters, and a plurality of connection pads located at an edge adjacent to the first side of the substrate and at an edge adjacent to the second side of the substrate. The plurality of connection pads is connected to the plurality of emission control signal lines.

Abstract: A display device includes a substrate including a first surface and a second surface opposite to the first surface, a display on the first surface, a first wiring pad located on the second surface and electrically connected to the display, an external connection terminal on the second surface, connection wiring located on the second surface and electrically connecting the first wiring pad and the external connection terminal, and a dummy conductor being a protrusion on the second surface. The protrusion overlaps none of the first wiring pad, the external connection terminal, and the connection wiring in a plan view.

Abstract: A travel assistance device according to the present invention comprises: a region extraction unit (11) that extracts a specific region that includes traffic participants around a host vehicle from image information of sensor data; a risk derivation unit (15) that derives the degree of risk for safe travel of the host vehicle in relation to the traffic participants in the extracted specific region; a priority-setting unit (16) that sets the processing priority of the specific region according to the degree of risk; a processing-load-setting unit (18) that sets the processing load of information of the specific region according to the processing priority; and a recognition-processing unit (19) that performs traffic participant recognition on the basis of processing load information from the processing-load-setting unit.

Abstract: A display device includes a substrate including a first surface, a side surface, and a second surface opposite to the first surface, a pixel unit located on the first surface and including a light emitter, a first connection pad adjacent to an edge on the first surface and electrically connected to the pixel unit, a second connection pad adjacent to the edge on the second surface, and a side wire extending from the first surface through the side surface to the second surface and connecting the first connection pad and the second connection pad. The first connection pad and the second connection pad have different sizes.

Abstract: A software verification system and the like that can facilitate improvement of software using sensor data of a vehicle as an input are provided. The software verification system detects (performance determining unit 118) a degradation of a new version of control software using, first information that is an output of a current version of control software used for control of a vehicle using, as an input, sensor data from a sensor mounted on the vehicle, second information that is an output of the new version of control software not used for the control of the vehicle using, as an input, the sensor data, and third information relating to the control of the vehicle other than the first and second information; and verifies the new version of control software by using the sensor data when the degradation is detected.

Abstract: A sound propagation characteristics correction apparatus includes: a pseudo inverse filter generation unit that generates a pseudo inverse filter by a function that smooths sound propagation characteristics from a speaker driver of a wearable open-ear speaker to an ear canal entrance; and an acoustic signal correction unit that corrects an acoustic signal on the basis of the pseudo inverse filter and transmits the corrected acoustic signal to the wearable open-ear speaker.

Abstract: A channel in which an utterance of a keyword is included is selected from acoustic signals of multiple channels. An addition unit 11 adds all channels of input voice signals of multiple channels to generate a composite voice signal of one channel. A keyword detection unit 12 generates a keyword detection result indicating a result of detecting an utterance of a predetermined keyword from a composite voice signal. A power calculation unit 13 calculates powers of channels based on input voice signals. A delay unit 14 delays the powers of the channels. When the keyword detection result indicates that the keyword was detected, a maximum power detection unit 15 selects, as an output channel, a channel having the maximum power among the powers of the channels of the input voice signals. A channel selection unit 16 selects the voice signal of the output channel from the input voice signals and outputs the selected voice signal.

Abstract: The present invention provides a novel therapeutic or prophylactic agent for psoriasis. This therapeutic or prophylactic agent for psoriasis contains a serotonin 4 receptor agonist.

Abstract: A channel in which an utterance of a keyword is included is selected from acoustic signals of multiple channels. An addition unit 11 adds all channels of input voice signals of multiple channels to generate a composite voice signal of one channel. A keyword detection unit 12 generates a keyword detection result indicating a result of detecting an utterance of a predetermined keyword from a composite voice signal. A power calculation unit 13 calculates powers of channels based on input voice signals. A delay unit 14 delays the powers of the channels. When the keyword detection result indicates that the keyword was detected, a maximum power detection unit 15 selects, as an output channel, a channel having the maximum power among the powers of the channels of the input voice signals. A channel selection unit 16 selects the voice signal of the output channel from the input voice signals and outputs the selected voice signal.

Abstract: A multi-display includes a first display device and a second display device. The first display device includes a first substrate including a first display surface and a first side surface continuous with the first display surface, a first display portion on the first display surface, and a first side wiring extending from the first side surface to the first display surface. The second display device includes a second substrate including a second display surface and a second side surface continuous with the second display surface, a second display portion on the second display surface, and a second side wiring extending from the second side surface to the second display surface. The first side surface and the second side surface are adjacent to and face each other. The first side wiring and the second side wiring are located without facing each other.

Abstract: Processing time of a neural network is shortened, and the number of operations of the neural network is reduced such that a plurality of calculators can be effectively used. A neural network reduction device (100) that reduces the number of operations of a neural network by an operation device (140) including a plurality of calculators by reducing the neural network, the neural network reduction device including: a calculator allocation unit (102) that sets the number of calculators allocated to calculation processing of the neural network; a number-of-operations setting unit (103) that sets the number of operations of a reduced neural network based on the number of allocated calculators; and a neural network reduction unit (104) that reduces the neural network such that the number of operations of the neural network by the operation device (140) is equal to the number of operations set by the number-of-operations setting unit (103).

Abstract: An electric compressor includes a rotary shaft, a compression part, a motor, an inverter that has an inverter circuit, and a housing. The housing includes a motor housing having a peripheral wall extending in an axial direction of the rotary shaft and a bottom wall, an inverter housing that is provided on the peripheral wall, a compression part housing, a shaft support member that has an insertion hole. The inverter housing has an extending portion extending in the axial direction away from the peripheral wall and having a high voltage connector and a low voltage connector. The high voltage connector and the low voltage connector are overlapped with the bottom wall as viewed in the axial direction and disposed within a width of the extending portion.

Abstract: An image recognition system according to one aspect of the present invention includes: a discrepancy information extraction unit that receives each of inference results of old and new machine learning models for the same input image, and outputs, when there is a discrepancy area in the two inference results, image information of the discrepancy area in the input image and information indicating presence or absence of detection of a point of interest in the discrepancy area by the new machine learning model; an object presence/absence determination unit that determines whether a point of interest is included in the image information of the discrepancy area and outputs a determination result; and a performance degradation determination unit that determines performance degradation of the new machine learning model compared with the current machine learning model based on the information indicating the presence or absence of detection of a point of interest in the discrepancy area by the new machine learning mode