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 input device with a display configured to display frames according to a vertical synchronization (Vsync) signal, a plurality of sensor electrodes, and a touch controller are provided. The touch controller is configured to drive a first subset of the plurality of sensor electrodes for sensing in a plurality of sequences. A default sequence includes a first sensing mode and a second sensing mode wherein the first sensing mode precedes the second sensing mode. In a modified sequence, the second sensing mode precedes the second sensing mode. The touch controller monitors timing of the Vsync signal and determines whether communication with a system component will interfere with one of the first sensing mode or the second sensing mode based on the timing of the Vsync signal. The touch controller drives the sensor electrodes in the default sequence or the modified sequence based on the determination. The touch controller also receives resulting signals from a second subset of the plurality of sensor electrodes.

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. The detection may be performed on the raw image data or may be performed as part of the compression process after a transformation of the raw image data has been carried out.

Abstract: A method of computing a floating point reciprocal value may eliminate the need for specialized hardware. One or more masks may be created and one or more comparison values may be defined, the comparison values based on a floating point input value. A mantissa and an exponent may be generated, and a reciprocal value may be computed based on the masks, the comparison values, the floating point input value, the mantissa and the exponent. Use of a considerably smaller lookup table for use only in computing the mantissa considerably reduces the number of memory accesses and cycles required for computing the floating point reciprocal.

Abstract: A method, device, and system of centralized coordination for switching between a primary channel and a non-primary channel using the access point. After detection of overlapping basic service set (OBSS) interference on the primary channel, the access point sends a channel switch request to all associated stations using overlapping basic service set (OBSS) packet detection (PD)-based spatial reuse (SR). The access point determines which stations received the channel switch request based on responses from the stations on either the primary channel or the non-primary channel. The access point may then communicate with responding stations on the non-primary channel.

Abstract: An input device and method with grasp detection are provided. The input device includes a display having a sensing region with a plurality of sensing electrodes. The input device also includes a rotatable interface. The rotatable interface includes interface electrodes configured to signal rotation of the rotatable interface. The input device also includes a processing system, which is configured to drive a first plurality of sensing electrodes with sensing signals during a first sensing period; determine, from first resulting signals, grasp of the rotatable interface; drive a second plurality of sensing electrodes with sensing signals during a second sensing period; and determine, from second resulting signals, rotation of the rotatable interface.

Abstract: This disclosure provides methods, devices, and systems for image encoding. The present implementations more specifically relate to progressive encoding techniques for autoencoders. In some aspects, an image encoder may encode an image as a tensor of latent attributes having multiple channels based on one or more first layers of a neural network model, and recombine the tensor channels, in a prioritized order, based on one or more second layers of the neural network model. The image encoder may progressively transmit the recombined tensor channels over a communication channel based on the prioritized order. In some implementations, the image encoder may transmit the recombined tensor channels, in order of priority, so that channels assigned higher priorities are transmitted before channels assigned lower priorities.

Abstract: The present disclosure relates to a method of managing display data in a system comprising a host device and a plurality of client devices connected to the host device. The method comprises receiving display data from at least one client device of the plurality of client devices at the host device via a shared connection between the plurality of client devices and the host device; generating, at the host device, control information for controlling generation, encoding and/or transmission of the display data by the at least one client device of the plurality of client devices; and transmitting the control information from the host device to the at least one client device of the plurality of client devices.

Abstract: A method, device, and system for audio signal processing is related to detecting and cancelling wind noise in an audio signal. In the presence of wind noise the energies of the different microphones are uncorrelated. The coherence of audio signals from at least two microphones, accordingly, may be determined and used to detect the presence of wind noise. If wind noise is detected, the coherence of the audio signals may be used to filter the audio signal to cancel the wind noise from the audio signal. The filter may determine a non-stationary noise gain based on the coherence of the audio signals, and a stationary noise gain based at least partially on the non-stationary noise gain and may apply the non-stationary noise gain and the stationary noise gain to the audio signal to remove the wind noise.

Abstract: Adaptive check and control logic and processes are used for monitoring performance of an integrated circuit by directly determining at least one of setup margins, hold margins, and voltage margins in one or more critical paths of the integrated circuit. The data state of the start and end points of the critical path are preserved prior to an adaptive test and the functional clock for the integrated circuit is gated. The adaptive test is performed by loading test data into the start point of the critical path and using an adaptive test clock to capture the test data at the end point of the critical path. The captured data is compared to expected values to detect timing violations. When the adaptive test is completed, the data state of the start and end points of the critical path are reloaded and the function clock for the integrated circuit is enabled.

Abstract: Methods and apparatus for configuring input/output (IO) signals are disclosed. An example method is performed by an IO controller and includes receiving instructions for acting on one or more IO pins of a plurality of IO pins associated with the IO controller, identifying an IO group corresponding to the one or more IO pins, setting a state of one or more bits of at least one control register of a plurality of control registers based at least in part on the identified IO group, and performing a first action on the one or more IO pins based at least in part on the received instructions and the identified IO group.

Abstract: A method, device, and system for audio signal processing is related to nonlinear post-processing filter to enhance the suppression of interference in audio signals. A nonlinear post filter suppresses residual interference, e.g., noise or echoes, in a target signal produced by a linear filter based on the target signal, which includes the residual interference, and a noise signal that represents the interference that was removed from the raw microphone audio signal by the linear filter. The nonlinear post filter refines the noise signal by scaling the noise signal when no speech is detected and removing residual speech in the scaled noise signal when speech is detected. A gain filter to suppress residual interference in the target signal is generated using the refined noise signal and the target signal, and is applied to the target signal to produced an enhanced audio signal with residual interference suppressed.

Abstract: A method performed by a docking station operable in a plurality of modes is disclosed. The method may include obtaining first data via a first interface of the docking station and second data via a second interface of the docking station, responsive to operating in a first mode of the plurality of modes. The first interface may be configured to couple the docking station to a computing device, and the second interface may be configured to communicate with a network. The method may also include obtaining third data via the second interface of the docking station, in lieu of the first interface, responsive to operating in a second mode of the plurality of modes. The method may further include selectively outputting the first data and the second data, or the third data, to a display based on whether the docking station operates in the first mode or the second mode.

Abstract: A method, device, and system for audio signal processing is related updating filter parameters for a filter for adaptive online processing based on supervision of Voice Activity Detection (VAD), which may be delayed in the detection of the onset of speech in the audio signal. Multiple versions of the filter parameters are stored including lagged filter parameters, which are older than current filter parameters. When speech is detected in the audio signal by the VAD, the filter is updated with the lagged filter parameters, which are older than the delay in the detection of the onset of speech to ensure the filter is updated with filter parameters generated during noise frames. When speech is not detected in the audio signal, the filter is updated with the current filter parameters. The lagged filter parameters and current filter parameters are periodically updated when no speech is detected in the audio signal.

Abstract: An integrated radio frequency switching circuit includes a radio frequency (RF) input/output (RFIO) that is configured to be operatively coupled to multiple RF paths. A Wireless Local Area Network (WLAN) transmission path includes a power amplifier and a WLAN power amplifier matching network circuit that are operatively coupled to the RFIO without a switch. An inductor in the WLAN power amplifier matching network is shunted to ground for electrostatic discharge (ESD) protection of the RFIO in all operational modes. A Personal Area Network (PAN) transmission path includes two power amplifiers with different power levels that are both operatively coupled to the RFIO through a series switch. A WLAN/PAN signal reception path includes a low noise amplifier (LNA) and an LNA matching network that are coupled to the RFIO. The series switch and a LNA matching network are controlled to enable multiple transmission and reception operational modes.

Abstract: This disclosure provides methods, devices, and systems for controlling a mode of operation associated with a wireless communication link. In some implementations, a controller module of a first wireless communication device may establish a link with a second wireless communication device; switch between an active mode associated with the link and a sniff mode associated with the link without sending to a host module of the first wireless communication device a message associated with the switching between the active mode and the sniff mode; determine that the link is idle for at least a threshold duration; and in response to determining that the link is idle for at least the threshold duration, switch a mode of operation associated with the link, from an active mode to a sniff mode, without sending to the host module a message associated with the switching to the sniff mode.

Abstract: Methods and apparatus for multilink wireless communication are disclosed. An example method is performed by a wireless communication system including a first wireless communication core and a second wireless communication core and includes identifying a plurality of packets for transmission via at least one of a first wireless transmitter associated with the first wireless communication core and a second wireless transmitter associated with the second wireless communication core, the first wireless communication core and the second wireless communication core coupled via a coexistence interface, selecting a first portion of the plurality of packets for transmission via the first wireless transmitter and a second portion of the plurality of packets for transmission via the second wireless transmitter, and transmitting the first portion of the plurality of packets via the first wireless transmitter and the second portion of the plurality of packets via the second wireless transmitter.

Abstract: Methods and apparatus for offloading wireless connections are disclosed. An example method includes configuring a wireless offload engine to maintain a wireless connection on behalf of one or more circuits coupled to the wireless offload engine, determining that the one or more circuits are to enter a low-power state, and maintaining the wireless connection after the one or more circuits have entered the low-power state based at least in part on the configuring.

Abstract: This disclosure provides methods, devices, and systems for image processing. The present implementations more specifically relate to object identification using high resolution images. In some implementations, an image analysis system may obtain a source image; detect one or more objects of interest in the source image; obtain a first portion of the source image based on the one or more detected objects of interest and a buffer size associated with detecting the one or more objects of interest in the source image; demosaic the first portion of the source image; and perform one or more image processing operations based on the demosaiced first portion of the source image.

Abstract: A system and method for transmitting signals using an input device is provided. The input device comprises a display and a touch sensor. The touch sensor has a plurality of sensor electrodes and a sensor circuit. The plurality of sensor electrodes are configured to transmit a periodic signal corresponding to a first waveform and a second waveform. The sensor circuit has a first charge pump configured to generate the first waveform to drive a first set of sensor electrodes of the plurality of sensor electrodes, and a second charge pump to configured generate the second waveform to drive a second set of sensor electrodes, different from the first set of sensor electrodes.