A noise reduction method and a noise reduction apparatus are provided. The noise reduction method is applied to a keyboard of an integrated terminal device, and the noise reduction method includes: obtaining a first voice source and a second voice source, where the first voice source is a fidelity voice source, the second voice source is an audio signal that includes the first voice source and a noise signal, and the noise signal comes from noise generated by vibration of the keyboard, and/or the noise signal comes from noise of an environment in which the integrated terminal device is located; determining the noise signal based on the first voice source and the second voice source. Based on the technical solutions in this application, the noise signal generated by the integrated terminal device can be offset, so that noise reduction processing is implemented and user experience is improved.

A portable fan configured with a high-speed three-phase motor is provided, the portable fan includes: a control module, a drive module, and the high-speed three-phase motor. The high-speed three-phase motor has an operating voltage of 2V to 18 V and an operating current of 0.1 to 10 A, and/or has a rated operating power of 0.5 to 100 W. The control module is configured to control, via the drive module and based on the operating voltage, the operating current, and/or the rated operating power, a rated operating rotation speed of the high-speed three-phase motor to reduce noise generated due to a high rotation speed of the high-speed three-phase motor and to control an air speed to be within a preset air speed range.

Systems and methods are provided an audio signal enhancement system that attenuates platform fan noise. Fan noise is a common type of self-noise in laptops and other devices, and fan noise can significantly degrade the quality of audio captured by built-in microphones. A neural network model is provided that enhances microphone Signal-to-Noise Ratio (SNR) and Signal-to-Distortion-plus-Noise Ratio (SDNR). The systems and methods also reduce algorithmic latency. The model architecture includes a Recurrent Neural Network, and a custom Gated Recurrent Unit layer is provided that uses fewer unique matrix weights and fewer biases and has fewer compute operations using fewer parameters. A platform self-noise suppression system is provided that eliminates low-amplitude platform self-noise signals. The model can predict when the platform fan is active, and remove the platform noise. In some examples, when the model predicts that the platform fan is not active, the model focuses on removing microphone self-noise.

Examples of the disclosure describe systems and methods for reducing audio effects of fan noise, specifically, for a wearable system. A method wherein operating a fan of a wearable head device; detecting, with a microphone of the wearable head device, noise generated by the fan; generating a fan reference signal, wherein the fan reference signal represents at least one of a speed of the fan, a mode of the fan, a power output of the fan, and a phase of the fan; deriving a transfer function based on the fan reference signal and based further on the detected noise of the fan; generating a compensation signal based on the transfer function; and while operating the fan of the wearable head device, outputting, by a speaker of the wearable head device, an anti-noise signal, wherein the anti-noise signal is based on the compensation signal.

A separate active noise cancellation device is installed on an electronic device which includes a circuit board and a noise generating source. The separate active noise cancellation device includes an active noise cancellation controller, a microphone and a speaker, the active noise cancellation controller is installed on and electrically connected to the circuit board, the microphone and the active noise cancellation controller are separately installed, the microphone has a cable provided for electrically connecting the active noise cancellation controller, the microphone is arranged around the noise generating source, the speaker is electrically connected to the active noise cancellation controller and capable of issuing a noise cancelling sound to offset the noise generated by the noise generating source. In this way, the amount of noise may be accurately captured and reduced to overcome the annoying noise problem.

Described herein are active noise reduction (ANR) techniques for reducing noise produced by a fan(s) of a head-mounted display (HMD). An example process may include receiving data indicative of a noise that is being produced by the fan(s), determining, based at least in part on the data and using a model(s), one or more audio parameter values, and outputting, via one or more off-ear speakers of the HMD, a sound(s) having one or more audio characteristics based at least in part on the one or more audio parameter values to reduce the noise produced by the fan(s) at a location(s) of an ear(s) of the user of the HMD.

A noise cancellation system comprising an audio identification unit configured to identify audio to which a noise cancellation process is to be applied, an output generation unit configured to generate one or more noise cancellation signals in dependence upon the identified audio, and two or more audio output units each configured to reproduce a respective subset of the generated one or more noise cancellation signals, such that the two or more audio output units are configured to produce different outputs.

Examples of the disclosure describe systems and methods for reducing audio effects of fan noise, specifically, for a wearable system. A method wherein operating a fan of a wearable head device; detecting, with a microphone of the wearable head device, noise generated by the fan; generating a fan reference signal, wherein the fan reference signal represents at least one of a speed of the fan, a mode of the fan, a power output of the fan, and a phase of the fan; deriving a transfer function based on the fan reference signal and based further on the detected noise of the fan; generating a compensation signal based on the transfer function; and while operating the fan of the wearable head device, outputting, by a speaker of the wearable head device, an anti-noise signal, wherein the anti-noise signal is based on the compensation signal.