Abstract: A display driver comprises control circuitry configured to store a default gamma curve, determine a count of in-region pixels of a target pixel in a display panel and neighboring pixels of the target pixel, the in-region pixels being located in a predetermined region of the display panel, and determine a scale factor based on a ratio of the count of the in-region pixels to a total number of the target pixel and the neighboring pixels. The control circuitry also determines a modified gamma curve by scaling the default gamma curve with the scale factor. The display driver further comprises image processing circuitry configured to apply a gamma transformation based on the modified gamma curve to image data defined for the target pixel to generate output voltage data for the target pixel.

Abstract: A system for determining a fold angle of a foldable device includes a plurality of electrodes and a processing system.

Abstract: This disclosure provides methods, devices, and systems for object detection. The present implementations more specifically relate to region of interest (ROI) inferencing techniques that can be implemented using a single object detection model. In some aspects, a computer vision system maps a set of grid cells to an input image so that each grid cell includes a respective portion of the image, and where each of the grid cells is assigned a respective priority value. The system selects an ROI of the image based on the priority value assigned to each grid cell and performs, on the ROI, an inferencing operation associated with an object detection model. The system updates the priority values for one or more of the grid cells based on a result of the inferencing operation. The system then selects another ROI based on the updated priority values and perform the inferencing operation on the new ROI.

Abstract: Systems and methods for identifying audio events in one or more audio streams include the use of a cascade audio spotting system (such as a cascade keyword spotting system (KWS)) to reduce power consumption while maintaining a desired performance. An example cascade audio spotting system may include a first module and a high-power subsystem. The first module is to receive an audio stream from one or more audio streams, process the audio stream to detect a first target sound activity in the audio stream, and provide a first signal in response to detecting the first target sound activity in the audio stream. The high-power subsystem is to (in response to the first signal being provided by the first module) receive the one or more audio streams and process the one or more audio streams to detect a second target sound activity in the one or more audio streams.

Abstract: An apparatus for remote processing of raw image data receives the raw image data from a camera, such as a security camera. The apparatus includes a detection module to detect portions of the image data that contain possible regions of interest. Information indicating the portions that contain the possible regions of interest is then used during a compression process so that the portions that contain the possible regions of interest are compressed using one or more compression algorithms to facilitate further analysis and the remainder are treated differently. The compressed image data is then transmitted to a central system for decompression and further analysis. In some cases, the detection system may detect possible regions of interest which appear to be faces, but without performing full facial recognition. These parts of the image data are then compressed in such a way as to maintain as much facial detail as possible, so as to facilitate the facial recognition when it is carried out at the central server.

Abstract: This disclosure provides methods, devices, and systems for audio signal processing. The present implementations more specifically relate to multi-frame beamforming using neural network supervision. In some aspects, a speech enhancement system may include a linear filter, a deep neural network (DNN), a voice activity detector (VAD), and an IFC calculator. The DNN infers a probability of speech (pDNN) in a current frame of a single-channel audio signal based on a neural network model. The VAD determines whether speech is present or absent in the current audio frame based on the probability of speech pDNN. The IFC calculator may estimate an IFC vector based on the output of the DNN (such as the probability of speech pDNN) and the output of the VAD (such as an indication of whether speech is present in the current frame). The linear filter uses the IFC vector to suppress noise in the current audio frame.

Abstract: This disclosure provides methods, devices, and systems for signal processing. The present implementations relate more specifically to a spatio-temporal beamformer. In some aspects, a beamforming system may receive an audio signal via a plurality of microphones, the audio signal including a number (B) of frames for each of the plurality of microphones, each of the B frames for each of the plurality of microphones including a number (N) of time-domain samples. For a first microphone, the beamforming system may transform the B*N time-domain samples into B*N/2 first frequency-domain samples; transform the B*N/2 first frequency-domain samples into B*N/2 second frequency-domain samples; and determine a probability of speech associated with the B*N/2 second frequency-domain samples based on a neural network model. The beamformer system may determine a minimum variance distortionless response (MVDR) beamforming filter based at least in part on the probability of speech for the first microphone.

Abstract: This disclosure provides methods, devices, and systems for video compression. The present implementations more specifically relate to video compression techniques that account for spatial-temporal changes in pixel values. In some aspects, an encoder may determine a change importance factor (CIF) for each image tile of a current image to be encoded. The encoder may calculate the CIF for an image tile of the current image (the “current image tile”) based on a degree of variation among the pixel values in the current image tile, a degree of change between the current image tile and a respective image tile of a previously-encoded image (the “previous image tile”), and a degree of variation among the pixel values in the previous image tile. In some implementations, the encoder may determine whether to transmit each of the current image tiles to a receiving device based on the CIF associated with the respective image tile.

Abstract: This disclosure provides methods, devices, and systems for low-light imaging. In some implementations, an image processor may be configured to reduce or remove noise associated with an image based, at least in part, on a neural network. For example, the neural network may be trained to infer a denoised representation of the image. In some aspects, the image processor may scale the brightness level of the image to fall within a normalized range of values associated with the neural network. In some other aspects, a machine learning system may scale the brightness levels of input images to match the brightness levels of ground truth images used to train the neural network. Still further, in some aspects, the machine learning system may scale the brightness levels of the input images and the brightness levels of the ground truth images to fall within the normalized range of values during training.

Abstract: This disclosure provides methods, devices, and systems for video compression. The present implementations more specifically relate to video compression techniques that account for spatial-temporal changes in pixel values. In some aspects, an encoder may determine a change importance factor (CIF) for each image tile of a current image to be encoded. The encoder may calculate the CIF for an image tile of the current image (the “current image tile”) based on a degree of variation among the pixel values in the current image tile, a degree of change between the current image tile and a respective image tile of a previously-encoded image (the “previous image tile”), and a degree of variation among the pixel values in the previous image tile. In some implementations, the encoder may determine whether to transmit each of the current image tiles to a receiving device based on the CIF associated with the respective image tile.

Abstract: A display driver includes a bump array with a staggered bump arrangement, a data compensation circuit, and driver circuitry. The data compensation circuit processes input pixel data for a pixel of a display panel to generate compensated pixel data. The driver circuitry generates a data voltage based on the compensated pixel data and output the data voltage to the pixel via a bump of the bump array. The processing of the input pixel data is based on a location of the bump in the bump array.

Abstract: A display driver includes image processing circuitry and drive circuitry. The image processing circuitry is configured to generate first voltage data for a first pixel in a first screen area of a display panel using a first gamma parameter. The image processing circuitry is further configured to generate second voltage data for a second pixel in a second screen area of the display panel using a second gamma parameter set. The image processing circuitry is further configured to determine an interpolated gamma parameter set for a third pixel in a connection area of the display panel through interpolation between the first gamma parameter set and the second gamma parameter set. The connection area is disposed between the first screen area and the second screen area. The image processing circuitry is further configured to generate third voltage data for the third pixel using the interpolated gamma parameter set.

Abstract: This disclosure provides methods, devices, and systems for video coding. The present implementations more specifically relate to hybrid coding techniques that combine aspects of inter-frame coding with aspects of intra-frame coding. In some aspects, a video encoder may perform inter-frame coding in a weighted manner so that the coded video frames (also referred to as “residual frames”) may include contributions from the current video frame to be transmitted over a communication channel and also may include contributions from the previous video frame transmitted over the communication channel. More specifically, any pixel value (r(n)) in the residual frame can be expressed as a weighted combination of a respective pixel value (x(n)) in the current video frame and a co-located pixel value (x(n?1)) in the previous video frame, where r(n)=x(n)??·x(n?1) and where 0???1 is a scaling factor representing the degree of contribution by the previous video frame.

Abstract: This disclosure provides methods, devices, and systems for audio signal processing. The present implementations more specifically relate to multi-pass neural networks configured for speech enhancement. In some aspects, a speech enhancement system may include a deep neural network (DNN) and a statistical signal processor (SSP). The DNN is configured to receive an input audio signal and infer a speech signal representing a speech component of the input audio signal based on a neural network model. The SSP is configured to further denoise the speech signal output by the DNN based on one or more statistical signal processing operations. In some implementations, the denoised speech signal may be fed back into the DNN (as an input audio signal) for further speech enhancement. As such, the speech enhancement system may recursively filter or suppress residual noise in the speech signal over a number of passes or iterations of a feedback loop.

Abstract: A processing system includes sensor circuitry and processing circuitry. The sensor circuitry is configured to, using the sensor electrodes, obtain capacitive measurements of a sensing region, and obtain a resistance measurement of the sensing region. The processing circuitry is coupled to the sensor circuitry. The processing circuitry is configured to determine a location of an input object using the capacitive measurements of the sensing region and determine a force value based on the resistance measurement and the location of the input object. Determining the force value mitigates a temperature variation of the sensing region affecting the resistance measurement. The processing circuitry is further configured to report the force value.

Abstract: This disclosure provides methods, devices, and systems for data compression. The present implementations more specifically relate to encoding techniques for compressing probability tables used for entropy coding. In some aspects, an entropy encoder may encode a probability table so that one or more contexts are represented by fewer bits than would otherwise be needed to represent the frequency of each symbol as a proportion of the total frequency of all symbols associated with such contexts. For example, if a given row of the probability table (prior to encoding) includes a number (M) of entries each having a binary value represented by a number (K) of bits, the same row of entries may be represented by fewer than M*K bits in the encoded probability table.

Abstract: A display driver includes image processing circuitry and drive circuitry. The image processing circuitry is configured to determine a total current of a display panel and perform an IR-drop compensation using the total current and a first graylevel for a first subpixel of the display panel to determine a first voltage level for the first subpixel. The drive circuitry is configured to update the first subpixel based at least in part on the first voltage level.

Abstract: A method is provided. The method comprises: providing, by a control system of an input device, one or more first beacon signals to an input object; based, at least in part, on force data from the input object, detecting, by the control system, noise interference associated with providing at least one of the one or more first beacon signals to the input object; based, at least in part, on detecting the noise interference, altering, by the control system, a timing schedule for providing one or more subsequent beacon signals; and providing, by the control system, the one or more subsequent beacon signals to the input object based, at least in part, on the timing schedule.

Abstract: A sensor assembly includes a cover layer and a first sensor apparatus. The cover layer is molded from a first material to have a planar surface and non-uniform thickness, where a thickness of the first material at a first region of the cover layer is less than a thickness of the first material surrounding the first region. The first sensor apparatus is disposed beneath the planar surface of the cover layer, within the first region. The first sensor apparatus is configured to transmit and receive first capacitive sensing signals through a portion of the planar surface coinciding with the first region. For example, the first sensor apparatus may be a fingerprint sensor configured to detect a fingerprint on the portion of the planar surface coinciding with the first region based on changes in the first capacitive sensing signals.

Abstract: A memory device includes a first word and a second word. The first word has a first subset of a plurality of elements. The first subset of the plurality of elements each have a first set of sequential index values along a first dimension of a tensor, a first single index value for a second dimension of the tensor, and a second single index value for a third dimension of the tensor. The second word has a second subset of the plurality of elements. The second subset of the plurality of elements each have the first set of sequential index values along the first dimension of the tensor that is the same as the first word, the first single index value for the second dimension of the tensor that is the same as the first word, and a third single index value for the third dimension of the tensor that is different than the second single index value for the first word. The second word is adjacent to the first word in memory.