A system method provides for multi-port wind noise protection. A sound may include a desired component such as speech and an undesired component such as wind. Multiple apertures on a housing receive the sound and conduct it to a microphone. The undesired component such as wind is uncorrelated at the apertures and mixes at the microphone, attenuating in amplitude while the desired component such as speech is correlated at the apertures. In this manner, the signal to noise ratio between the desired component and undesired component is improved at the microphone.

A recurrent neural network is employed in a loudspeaker system to compensate the distortion of the system based upon a source signal (content) and the sensing output of a sensing circuit (context). A frequency domain transform is selected to provide mapping between the source signal and a recorded signal; and enable reconstruction of desirable playback. Various sensing-related features and source-related features are derived to serve as the auxiliary information. A desirable content is therefore generated based upon the original content and the context.

Certain aspects of the present disclosure are generally directed to circuitry and techniques for current sensing. For example, certain aspects provide a circuit for signal amplification including a first amplifier, a second amplifier, and a third amplifier. The circuit also includes a first capacitive element coupled between a first output of the first amplifier and a first input of the third amplifier, a second capacitive element coupled between a second output of the first amplifier and a second input of the third amplifier, a third capacitive element coupled between a first output of the second amplifier and the first input of the third amplifier, and a fourth capacitive element coupled between a second output of the second amplifier and the second input of the third amplifier.

A method for detecting ambient noise to change the playing voice frequency and a sound playing device thereof are disclosed. The method includes the following steps: obtaining an input voice; detecting an ambient noise, and analyzing a noise frequency range of the ambient noise; determining whether a consonant frequency range of the input voice falls within the noise frequency range; if yes, adjusting the frequency of the consonant of the input voice to avoid the noise frequency range to form a modified voice; and playing an output voice, wherein the output voice includes the modified voice.

An audio system for a wearable device dynamically updates acoustic transfer functions. The audio system is configured to estimate a direction of arrival (DoA) of each sound source detected by a microphone array relative to a position of the wearable device within a local area. The audio system may track the movement of each sound source. The audio system may form a beam in the direction of each sound source. The audio system may identify and classify each sound source based on the sound source properties. Based on the DoA estimates, the movement tracking, and the beamforming, the audio system generates or updates the acoustic transfer functions for the sound sources.

A nonlinear control system and a speaker protection system are disclosed. In particular, a control system for adapting an audio output from a speaker in the proximity of an object is disclosed. The controller is configured to accept one or more input signals, and one or more estimated states produced by the model to produce one or more control signals. A speaker protection system and a quality control system are disclosed. More particularly, a system for clamping the input to a speaker dependent upon an estimate of the proximity, acoustic volume, and/or acoustic coupling of the speaker to a nearby object is disclosed.

Aspects of the disclosure relate to using a display as a sound emitter and may relate to an electronic device including a display. In particular a vibration sensor such as an accelerometer is physically coupled to the display and senses display vibration to provide a high accuracy feedback loop with respect to representing actual audio output from the display. The electronic device includes an actuator physically coupled to the display and configured to cause vibration of the display in response to an audio signal. The electronic device further includes a vibration sensor physically coupled to the display and configured to output a vibration sensor signal proportional to the vibration of the display due to the actuator.

A speaker has a magnetic angle sensor that detects the displacement of the vibration system of the speaker. A non-linearity compensation filter compensates for output distortion due to a non-linear parameter of the speaker. A transfer function of a linear inverse filter is applied so that output distortion is eliminated from the displacement, detected by the magnetic angle sensor, of the vibration system. A controller drives the speaker by using a test signal, and measures a response from the detected displacement of the vibration system. If error between the measured response and the theoretical value, theoretically determined from the design specifications, of the response is small, the controller uses the theoretical value, theoretically determined from the design specifications, of the non-linear parameter as an active non-linear parameter and sets, in the non-linearity compensation filter, a transfer function that compensates for distortion in an output due to the active non-linear parameter.

An audio system includes a speaker and a processor. The processor determines a privacy setting for an audio signal. The privacy setting may be selected by a user. The privacy setting may indicate activation of a private mode, or may indicate a privacy level from a range of privacy levels. The processor determines an audio filter that adjusts the audio signal to mitigate sound leakage when presented by the speaker based on the privacy setting. The audio filter may include a low-pass filter and a multiband compressor. The parameters of the audio filter may vary based on the privacy setting. The processor applies the audio filter to the audio signal to generate a filtered audio signal and provides the filtered audio signal to the speaker.

A method for determining a direct current impedance of a transducer may include receiving an input signal indicative of an electrical power consumed by the transducer and calculating, by a thermal model of the transducer, the direct current impedance based on the electrical power.