Abstract: This application provides an electrode plate mass detection method, coating method, apparatus, device, system, and medium, pertaining to the field of battery technologies. The method includes: controlling a surface density gauge to create radiation surfaces of different shapes on an electrode plate; obtaining surface density information corresponding to the radiation surfaces; and determining mass information of the electrode plate based on the surface density information.

Abstract: A system and method of generating binaural signals includes receiving, by a processing device, a sound signal including speech and noise components, and transforming, by the processing device using a deep neural network (DNN), the sound signal into a first signal and a second signal. The transforming further includes encoding, by an encoding layer of the DNN, the sound signal into a sound signal representation in a latent space, rendering, by a rendering layer of the DNN, the sound signal representation into a first signal representation and a second signal representation in the latent space, and decoding, by a decoding layer of the DNN, the first signal representation into the first signal and the second signal representation into the second signal.

Abstract: A beamformer, for a differential microphone array (DMA) including a number M of microphones, is constructed based on a specified target directivity factor (DF) value for the DMA. An N order beampattern is generated for the DMA, wherein N is an integer and a first DF value corresponding to the N order beampattern is greater than the target DF value. An N?1 order beampattern is generated for the DMA, wherein a second DF value corresponding to the N?1 order beampattern is greater than the target DF value. A fractional order beampattern is generated for the DMA, wherein a third DF value corresponding to the fractional order beampattern matches the target DF value and the fractional order beampattern comprises a first fractional contribution from the N order beampattern and a second fractional contribution from the N?1 order beampattern.

Abstract: A battery powered electronic device can include a battery to power one or more loads, a first DC-DC converter having an input coupled to the battery and an output, and a second DC-DC converter cascaded with the first DC-DC converter and coupled to a second load subject to pulsed operation. The first and second converters may be configured so as to isolate the one or more loads from transients associated with the pulsed operation of the second load. The second converter may have an input coupled to the output of the first converter and an output coupled to the second load. Alternatively, the second converter may be a bidirectional converter having first terminals coupled to the output of the first converter and second terminals coupled to an energy storage device.

Abstract: Implementations of the present specification disclose methods, apparatuses, and devices for training an object detection system by using a gradient fine-tuning technique. In one aspect, the method includes: providing a training image as input to the object detection system; processing the training image by the object detection system; determining a gradient norm of each neural network layer based on object annotation data and the detection result corresponding to the training image; and updating, for each neural network layer, parameter values of the neural network layer based on an average of gradient norms and the gradient norm of the neural network layer.

Abstract: Implementations of the present specification provide a video retrieval method and apparatus. In the method, a video frame in a video to be matched is obtained; an image feature and a text feature are extracted from the video frame; the image feature and the text feature are fused based on a center variable used to represent a cluster center to obtain a fused feature, where the center variable is used to associate features of different modes of a same video; and video retrieval is performed in a video database based on the fused feature to determine a video in the video database that matches the video to be matched, where a plurality of videos and video features corresponding to the plurality of videos are stored in the video database.

Abstract: A display device include a first light emitting diode (LED), a second LED, and at least one processor of a driver. The processor drives the first LED and the second LED. The processor determines a first pulse width associated with the first LED and a second pulse width associated with the second LED based on a level of brightness to be emitted by the first LED and the second LED. The processor also receives a gap clock and determines a first pulse start time and a first pulse end time for the first LED based on the first pulse width. Moreover, the processor determines a second pulse start time and a second pulse end time for the second LED based on the first pulse end time, the second pulse width, and/or the gap clock, in which the first pulse end time and the second pulse end time are different.

Abstract: Systems and methods for preserving a pulse width modulation (PWM) resolution while increasing the frequency of a pulse width modulation (PWM) clock are provided. An electronic display backlight system may include a backlight element and backlight dimming circuitry. The backlight element may be driven according to a pulse width modulation (PWM) signal over a PWM clock cycle equal to a multiple M of a baseline PWM clock frequency associated with a baseline PWM resolution. The backlight dimming circuitry may receive a brightness code of the baseline PWM resolution and generate the PWM signal at least in part by dividing the brightness code by M.

Abstract: A feature extraction deep neural network (DNN) may be trained based on the minimization of a loss function. A similarity function may be specified to calculate a similarity score for two representations of verbal utterances. A training data set comprising pairs of representations of utterances is received, wherein each one of the pairs of representations of utterances is associated with a corresponding a ground-truth label confirming whether the pair of represented utterances come from a same speaker or not. A respective similarity score may then be calculated for each one of the pairs of representations of utterances. Parameters associated with the DNN may then be updated based on minimizing a loss function associated with an area under a section of a receiver-operating-characteristic (ROC) curve for the similarity scores, wherein the ROC curve section is delimited between a low false positive rate (FPR) value and a high FPR value.

Abstract: A first-order differential microphone array (FODMA) with a steerable beamformer is constructed by specifying a target beampattern for the FODMA at a steering angle ? and then decomposing the target beampattern into a first sub-beampattern and a second sub-beampattern based on the steering angle ?. A first sub-beamformer and a second sub-beamformer are generated to each filter signals from microphones of the FODMA, wherein the first sub-beamformer is associated with the first sub-beampattern, and the second sub-beamformer is associated with the second sub-beampattern. The steerable beamformer is then generated based on the first sub-beamformer and the second sub-beamformer. The decomposing of the target beampattern into a first sub-beampattern and a second sub-beampattern includes dividing the target beampattern into a sum of a first-order cosine (cardioid) first sub-beampattern and a first-order sinusoidal (dipole) second sub-beampattern.

Abstract: Power converters can include a plurality of switching devices and a combination of one or more inductors and one or more flying capacitors. Both boost and buck converters may employ such topologies, and can achieve high efficiency and small size in at least some applications, including those with high conversion ratios. A control circuit can generate a first pair of complementary gate drive signals to drive a first complementary switch pairs and a second pair of complementary gate drive signals to drive a second complementary switch pair. The control circuit can vary a phase shift between the first pair of complementary gate drive signals and the second pair of complementary gate drive signals to regulate the flying capacitor voltage.

Abstract: Systems and methods for preserving a pulse width modulation (PWM) resolution while increasing the frequency of a pulse width modulation (PWM) clock are provided. An electronic display backlight system may include a backlight element and backlight dimming circuitry. The backlight element may be driven according to a pulse width modulation (PWM) signal over a PWM clock cycle equal to a multiple M of a baseline PWM clock frequency associated with a baseline PWM resolution. The backlight dimming circuitry may receive a brightness code of the baseline PWM resolution and generate the PWM signal at least in part by dividing the brightness code by M.

Abstract: A display device include a first light emitting diode (LED), a second LED, and at least one processor of a driver. The processor drives the first LED and the second LED. The processor determines a first pulse width associated with the first LED and a second pulse width associated with the second LED based on a level of brightness to be emitted by the first LED and the second LED. The processor also receives a gap clock and determines a first pulse start time and a first pulse end time for the first LED based on the first pulse width. Moreover, the processor determines a second pulse start time and a second pulse end time for the second LED based on the first pulse end time, the second pulse width, and/or the gap clock, in which the first pulse end time and the second pulse end time are different.

Abstract: A binaural beamformer comprising two beamforming filters may be communicatively coupled to a microphone array to generates two beamforming outputs, one for the left ear and the other for the right ear. The beamforming filters may be configured in such a way that they are orthogonal to each other to make white noise components in the binaural outputs substantially uncorrelated and desired signal components in the binaural outputs highly correlated. As a result, the human auditory system may better separate the desired signal from white noise and intelligibility of the desired signal may be improved.

Abstract: Power converters can include a plurality of switching devices and a combination of one or more inductors and one or more flying capacitors. Both boost and buck converters may employ such topologies, and can achieve high efficiency and small size in at least some applications, including those with high conversion ratios. A control circuit can generate a first pair of complementary gate drive signals to drive a first complementary switch pairs and a second pair of complementary gate drive signals to drive a second complementary switch pair. The control circuit can vary a phase shift between the first pair of complementary gate drive signals and the second pair of complementary gate drive signals to regulate the flying capacitor voltage.

Abstract: An Nth order linear differential microphone array (LDMA) with a steerable beamformer may be constructed by specifying a target beampattern for the LDMA at a steering angle ?. An Nth order polynomial associated with the target beampattern may then be generated. A relationship between the nulls of the polynomial and the steering angle ? is determined and then a value of one of the nulls is determined based on N?1 assigned values for the other nulls and the determined relationship between the nulls of the polynomial and the steering angle ?. The steerable beamformer may be generated based on the determined null value and the N?1 assigned null values. The N?1 assigned null values may be associated with the N?1 nulls of the polynomial that are of less than Nth order and the determined null value may be associated with the null of the polynomial that is of Nth order.

Abstract: An Nth order linear differential microphone array (LDMA) with a steerable beamformer may be constructed by specifying a target beampattern for the LDMA at a steering angle ?. An Nth order polynomial associated with the target beampattern may then be generated. A relationship between the nulls of the polynomial and the steering angle ? is determined and then a value of one of the nulls is determined based on N?1 assigned values for the other nulls and the determined relationship between the nulls of the polynomial and the steering angle ?. The steerable beamformer may be generated based on the determined null value and the N?1 assigned null values. The N?1 assigned null values may be associated with the N?1 nulls of the polynomial that are of less than Nth order and the determined null value may be associated with the null of the polynomial that is of Nth order.

Abstract: The present disclosure provides a low-cost and accurate rheometer system and method capable of determining melt flow rheological properties of polymers, such as from Fused Filament Fabrication (“FFF”) polymeric materials. The device can include a filament feeding system, liquefier for filament melting, force transducer for measuring filament feeding force, and a temperature control system for controlling polymer melt temperatures. An electronic control system can capture data and manage operations. The system can measure a filament velocity and filament force required to extrude the FFF filament for printing. The filament velocity and force data can be used to compute data sets of melt volumetric flow relative to pressure drop across a FFF nozzle.

Abstract: A pixel array may be illuminated with backlight illumination from a backlight. The backlight may include a two-dimensional array of light-emitting diodes, with each light-emitting diode being placed in a respective cell. Different light-emitting diodes may have unique brightness magnitudes based on the content of the given display frame. Driver integrated circuits may control one or more associated light-emitting diodes to have a desired brightness level. The driver integrated circuits may be formed in an active area of the backlight. The driver integrated circuits may be arranged in groups that are daisy chained together. A digital signal (that includes information such as addressing information) may be propagated through the group of driver integrated circuits. To manage thermal performance of the backlight, the backlight may include a thermally conductive layer and/or a heat sink structure. To increase the efficiency of the backlight, the backlight may include one or more reflective layers.

Abstract: A pixel array may be illuminated with backlight illumination from a backlight. The backlight may include a two-dimensional array of light-emitting diodes, with each light-emitting diode being placed in a respective cell. Different light-emitting diodes may have unique brightness magnitudes based on the content of the given display frame. Driver integrated circuits may control one or more associated light-emitting diodes to have a desired brightness level. The driver integrated circuits may be formed in an active area of the backlight. The driver integrated circuits may be arranged in groups that are daisy chained together. A digital signal (that includes information such as addressing information) may be propagated through the group of driver integrated circuits. To manage thermal performance of the backlight, the backlight may include a thermally conductive layer and/or a heat sink structure. To increase the efficiency of the backlight, the backlight may include one or more reflective layers.