Systems and methods for reducing vibrations perceived by a human due to an artificial heart valve include a vest that is wearable around a torso of the human, a plurality of sensors mounted to the vest, a plurality of vibration-generating actuators mounted to the vest, and a controller. The plurality of sensors detects vibrations in the human generated by the artificial heart valve. The controller is operable to receive signals representing the detected vibrations from the plurality of sensors, and is operable to produce anti-vibration signals that substantially attenuate the detected vibrations. A first sensor of the plurality of sensors is located near a first vibration-generating actuator of the plurality of vibration-generating actuators to form a sensor/actuator set. In the sensor/actuator set, the anti-vibration signals generated by the controller for the first vibration-generating actuator correspond to the vibrations detected by the first sensor.

An active noise control apparatus of vehicles capable of making it difficult for a passenger in a vehicle to hear the voice of another passenger, achieving privacy protection, and a method of controlling the same are disclosed. The active noise control method includes primarily determining a noise level based on a first microphone signal input through a microphone corresponding to a first seat, secondarily determining whether to output an anti-noise signal generated based on the first microphone signal and the magnitude of the anti-noise signal based on the noise level and the level of the first microphone signal, and outputting the anti-noise signal through a headrest speaker of a second seat in response to the secondary determining.

The present disclosure provides an acoustic device including a microphone array, a processor, and at least one speaker. The microphone array may be configured to acquire an environmental noise. The processor may be configured to estimate a sound field at a target spatial position using the microphone array. The target spatial position may be closer to an ear canal of a user than each microphone in the microphone array. The processor may be configured to generate a noise reduction signal based on the environmental noise and the sound field estimation of the target spatial position. The at least one speaker may be configured to output a target signal based on the noise reduction signal. The target signal may be used to reduce the environmental noise. The microphone array may be arranged in a target area to minimize an interference signal from the at least one speaker to the microphone array.

The present disclosure relates to a method for performing inference on input data using a neural network and a processing device employing the aforementioned method. The method comprises the steps of obtaining and storing input data, obtaining parameter data indicating the parameters of the first layer and storing the parameter data in a parameter data storage location and processing the input data using the first layer parameter data, to form first layer output data. The method further comprises storing the first layer output data, obtaining parameter data of the second layer and storing the second layer parameter data by replacing the first layer parameter data with the second layer parameter data, processing the first layer output data using the stored second layer parameter data to form second layer output data; and storing the second layer output data.

An active noise control apparatus of vehicles capable of making it difficult for a passenger in a vehicle to hear the voice of another passenger, achieving privacy protection, and a method of controlling the same are disclosed. The active noise control method includes primarily determining a noise level based on a first microphone signal input through a microphone corresponding to a first seat, secondarily determining whether to output an anti-noise signal generated based on the first microphone signal and the magnitude of the anti-noise signal based on the noise level and the level of the first microphone signal, and outputting the anti-noise signal through a headrest speaker of a second seat in response to the secondary determining.

The present disclosure provides an acoustic device including a microphone array, a processor, and at least one speaker. The microphone array may be configured to acquire an environmental noise. The processor may be configured to estimate a sound field at a target spatial position using the microphone array. The target spatial position may be closer to an ear canal of a user than each microphone in the microphone array. The processor may be configured to generate a noise reduction signal based on the environmental noise and the sound field estimation of the target spatial position. The at least one speaker may be configured to output a target signal based on the noise reduction signal. The target signal may be used to reduce the environmental noise. The microphone array may be arranged in a target area to minimize an interference signal from the at least one speaker to the microphone array.

A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.

Examples of system for ambient aversive sound detection, identification and management are described. The system comprises an earpiece device with a microphone configured to capture ambient sound around a user and sample it into small segments of the ambient sound, a speaker and a regulator to regulate the ambient sound segment transmitted to the speaker. The system further comprises a processing unit that identifies aversive ambient sound signals in the captured sound segment and provide recommendation action to manage the aversive sound signal by removing, supressing, attenuating or masking the aversive signals.

An apparatus for predicting an acceleration signal predicts an acceleration signal of an acceleration sensor installed on a vehicle for active noise control (ANC) and includes: a prediction module configured to train a predefined prediction algorithm to predict an acceleration signal after N samples compared to a point in time at which an acceleration signal is acquired by the acceleration sensor (N is a natural number), and to apply a reference acceleration signal acquired at a reference point in time to the completely trained prediction algorithm to generate a predicted acceleration signal after the N samples compared to the reference point in time; and an ANC module configured to perform ANC on the basis of the predicted acceleration signal generated by the prediction module.

A method for hybrid noise suppression includes receiving a processed audio signal from an audio device. The processed audio signal results from a partial audio processing performed on a noisy audio input signal. The method further includes predicting a noise suppression parameter using a neural network model operating on the processed audio signal and generating a noise-suppressed audio signal from the processed audio signal, using the noise suppression parameter. The method further includes generating a noise-suppressed audio output signal from the noise-suppressed audio signal using an additional audio processing and outputting the noise-suppressed audio output signal.