Abstract: An artificial intelligence (AI)-based constrained random verification (CRV) method for a design under test (DUT) includes: receiving a series of constraints; obtaining a limited constraint range according to the series of constraints; generating a series of stimuli according to the limited constraint range; and verifying the DUT by the series of stimuli; wherein at least one of the step of obtaining the limited constraint range according to the series of constraints and the step of generating the series of stimuli according to the limited constraint range employs an AI algorithm.

Abstract: A violation checking method includes generating a violation log report for a design, classifying violation logs in the violation log report into high-risk logs and low-risk logs by a machine learning model, reviewing the high-risk logs, and modifying the design if at least one bug is identified in the high-risk logs.

Abstract: An artificial intelligence (AI)-based constrained random verification (CRV) method for a design under test (DUT) includes: receiving a series of constraints; obtaining a limited constraint range according to the series of constraints; generating a series of stimuli according to the limited constraint range; and verifying the DUT by the series of stimuli; wherein at least one of the step of obtaining the limited constraint range according to the series of constraints and the step of generating the series of stimuli according to the limited constraint range employs an AI algorithm.

Abstract: A system performs the operations of a neural network agent and a circuit simulator for analog circuit sizing. The system receives an input indicating a specification of an analog circuit and design parameters. The system iteratively searches a design space until a circuit size is found to satisfy the specification and the design parameters. In each iteration, the neural network agent calculates measurement estimates for random sample generated in a trust region, which is a portion of the design space. Based on the measurement estimate, the system identifies a candidate size that optimizes a value metric. The circuit simulator receives the candidate size and generates a simulation measurement. The system calculates updates to weights of the neural network agent and the trust region for a next iteration based on, at least in part, the simulation measurement.

Abstract: A surveillance system includes an infrared sensor system coupled to output an infrared signal in response to receiving infrared light, and an audio recording system coupled to output an audio signal in response to recording sound. An image sensor is system coupled to output an image signal in response to receiving image light. A controller is coupled to the infrared sensor system, the audio recording system, and the image sensor system. The controller includes logic that when executed by the controller causes the surveillance system to perform operations including receiving the infrared signal from the infrared sensor system, activating the audio recording system to record the sound, and activating the image sensor system to output the image signal.

Abstract: An electronic device to equalize sound includes a microphone coupled to receive the sound and output sound data. The sound has amplitude that changes with respect to time, and the sound includes one or more frequencies. The sound data indexes the amplitude with respect to the time. The electronic device also includes a controller coupled to microphone, and the controller includes logic that when executed by the controller causes the electronic device to perform operations. The operations may include: receiving the sound data from the microphone with the controller; adjusting the amplitude of the sound included in the sound data across the one or more frequencies using a filter disposed in the logic; and outputting filtered sound data.

Abstract: A surveillance system includes an infrared sensor system coupled to output an infrared signal in response to receiving infrared light, and an audio recording system coupled to output an audio signal in response to recording sound. An image sensor is system coupled to output an image signal in response to receiving image light. A controller is coupled to the infrared sensor system, the audio recording system, and the image sensor system. The controller includes logic that when executed by the controller causes the surveillance system to perform operations including receiving the infrared signal from the infrared sensor system, activating the audio recording system to record the sound, and activating the image sensor system to output the image signal.

Abstract: An electronic device to equalize sound includes a microphone coupled to receive the sound and output sound data. The sound has amplitude that changes with respect to time, and the sound includes one or more frequencies. The sound data indexes the amplitude with respect to the time. The electronic device also includes a controller coupled to microphone, and the controller includes logic that when executed by the controller causes the electronic device to perform operations. The operations may include: receiving the sound data from the microphone with the controller; adjusting the amplitude of the sound included in the sound data across the one or more frequencies using a filter disposed in the logic; and outputting filtered sound data.

Abstract: Apparatuses and Methods of double talk detection for echo suppression in the power domain are disclosed herein. An example method includes comparing a power echo estimate signal to a microphone power signal, determining if the power echo estimate signal is greater than or less than the microphone power signal by a first threshold, based on the power echo estimate signal being greater than or less than the microphone power signal by the first threshold, disabling adaptation of filter coefficients of an adaptive filter of an echo suppressor, and based on the power echo estimate signal not being greater than or less than the microphone power signal by the first threshold, enabling adaptation of filter coefficients of an adaptive filter of an echo suppressor.

Abstract: A speaker system featuring automatic volume adjustment to avoid excess distortion includes a first converter for converting an input signal to an input frequency domain signal; and a second converter for converting a microphone signal to an environmental frequency domain signal. A distortion analyzer receives output of the first and second converter and determines at least one distortion level and provides at least one gain adjustment signal used to control a corrector to adjust gain of a speaker driver. The system performs a method of reducing distortion by automatically adjusting volume in each of a plurality of frequency bands including converting an input signal to a frequency domain input signal; converting a microphone signal to an environmental frequency domain signal; determining a distortion level; generating a gain adjustment signal; and adjusting gain of a signal provided to a speaker driver.

Abstract: Apparatuses and Methods of double talk detection for echo suppression in the power domain are disclosed herein. An example method includes comparing a power echo estimate signal to a microphone power signal, determining if the power echo estimate signal is greater than or less than the microphone power signal by a first threshold, based on the power echo estimate signal being greater than or less than the microphone power signal by the first threshold, disabling adaptation of filter coefficients of an adaptive filter of an echo suppressor, and based on the power echo estimate signal not being greater than or less than the microphone power signal by the first threshold, enabling adaptation of filter coefficients of an adaptive filter of an echo suppressor.

Abstract: A noise suppressor has a band extractor to separate signal by frequency band; and per-band units for each of band including noise estimator and SNR computation units. The per-band unit has a histogrammer to give histograms of current and past SNRs, and a gain-curve updater computes gain curves from the histogram. Gain curves are used to determine raw gains from current SNRs, raw gain is filtered and controls a variable gain unit to provide band-specific gain-adjusted, signals that are recombined into a noise-reduced frequency-domain output. Raw gain filtering may include finite-impulse-response filtering and weighted averaging of intermediate gains of a current and adjacent-band per-band unit. The method includes separating an input into frequency bands, estimating in-band noise, and deriving a band SNR. Then, histogramming the SNR and updating a gain curve from the histogram, and finding a raw gain using the gain curve and current SNR.

Abstract: A noise-level estimator for a noise suppressor includes a power smoother filter providing smoothed power estimates in timeslices, a minimum follower that represents the lowest smoothed input power, and a maximum follower that represents the highest smoothed input power, the followers subject to leakage factors. The estimator has a speech probability detector receiving outputs of the power smoother and minimum follower; a nonstationary noise detector receiving outputs of both followers; and an estimator receiving outputs of the nonstationary noise detector, power smoother, and speech probability detector and providing a noise estimate.

Abstract: An echo canceller includes a fast Fourier transform (FFT) unit to provide frequency domain representation (FD) of an input. A multiband adaptive filter receives the FD of the input and provides an FD filter output, the adaptive filter is a finite input response (FIR) digital filter. Another FFT unit provides an FD of a microphone signal, and a summer adds the FD filter output to the FD of the microphone signal to provide echo-canceller FD output. A feedback subsystem uses the echo-canceller FD output to adjust filter coefficients of at least a first, a second, and a third frequency band of the multiband adaptive filter to minimize uncancelled output in the echo-canceller FD output. The feedback subsystem adjusts the filter coefficients of the second frequency band of the adaptive filter according to uncancelled output in the first, second, and third frequency bands of the echo-canceller FD output.

Abstract: In a method of fabricating graphite flakes applied in a graphite nanomaterial, mesophase pitch and an organic solvent are used to produce a carbon precursor slurry, and the carbon precursor slurry is coated by a scraper to produce the graphite flakes. Since the method of using natural graphite as a raw material in production requires a number of purification processes to manufacture an expanded graphite powder before the graphite flakes can be produced, and thus the fabricating cost is very high, and other high-priced materials such as polyimide (PI) or graphene also will increase the total cost.

Abstract: A method for manufacturing graphene is disclosed, which comprises the following steps: putting graphite material and an organic solvent, a surfactant, or a combination thereof in a reaction tank and introducing a supercritical fluid in the reaction tank to allow the organic solvent, the surfactant, or the combination thereof to dissolve in the supercritical fluid and to permeate into the graphite material; and removing the supercritical fluid by depressurization to form graphene. The method of the present invention has simple steps and reduced consumption of manufacturing time, and also can promote the quality of the resultant graphene in large-scale manufacturing.

Abstract: A graphite-vinyl ester resin composite conducting plate is prepared in the present invention. The conducting plate can be used as a bipolar plate for a fuel cell, counter electrode for dye-sensitized solar cell and electrode of vanadium redox battery. The conducting plate is prepared as follows: a) compounding vinyl ester resin and graphite powder to form a bulk molding compound (BMC) material, the graphite powder content ranging from 70 wt % to 95 wt % based on the total weight of the graphite powder and vinyl ester, wherein 0.01-15 wt % functionalized graphene, based on the weight of the vinyl ester resin, are added during the compounding; b) molding the BMC material from step a) to form a conducting plate having a desired shaped at 80-250° C. and 500-4000 psi.

Abstract: A method for manufacturing graphene is disclosed, which comprises the following steps: putting graphite material and an organic solvent, a surfactant, or a combination thereof in a reaction tank and introducing a supercritical fluid in the reaction tank to allow the organic solvent, the surfactant, or the combination thereof to dissolve in the supercritical fluid and to permeate into the graphite material; and removing the supercritical fluid by depressurization to form graphene. The method of the present invention has simple steps and reduced consumption of manufacturing time, and also can promote the quality of the resultant graphene in large-scale manufacturing.