Some disclosed methods involve receiving microphone signals from a microphone system, including signals corresponding to one or more sounds detected by the microphone system. Some methods may involve determining, via a trained neural network, a filtering scheme for the microphone signals, the filtering scheme including one or more filtering processes. The trained neural network may be configured to implement one or more subband-domain adaptive filter management modules. Some methods may involve applying the filtering scheme to the microphone signals, to produce enhanced microphone signals.

Noises that are to be emitted by an aerial vehicle during operations may be predicted using one or more machine learning systems, algorithms or techniques. Anti-noises having equal or similar intensities and equal but out-of-phase frequencies may be identified and generated based on the predicted noises, thereby reducing or eliminating the net effect of the noises. The machine learning systems, algorithms or techniques used to predict such noises may be trained using emitted sound pressure levels observed during prior operations of aerial vehicles, as well as environmental conditions, operational characteristics of the aerial vehicles or locations of the aerial vehicles during such prior operations. Anti-noises may be identified and generated based on an overall sound profile of the aerial vehicle, or on individual sounds emitted by the aerial vehicle by discrete sources.

A computer-implemented method performed by an auditory device includes receiving a current location from a user device. The method further includes determining whether the current location exceeds a distance threshold from a previous location that is associated with a current preset. The method further includes responsive to the current location exceeding the distance threshold, determining whether one or more presets have been previously used in the current location by a user. The method further includes responsive to determining that the one or more presets have been previously used in the current location by the user, applying, with the auditory device, the one or more presets.

Noises that are to be emitted by an aerial vehicle during operations may be predicted using one or more machine learning systems, algorithms or techniques. Anti-noises having equal or similar intensities and equal but out-of-phase frequencies may be identified and generated based on the predicted noises, thereby reducing or eliminating the net effect of the noises. The machine learning systems, algorithms or techniques used to predict such noises may be trained using emitted sound pressure levels observed during prior operations of aerial vehicles, as well as environmental conditions, operational characteristics of the aerial vehicles or locations of the aerial vehicles during such prior operations. Anti-noises may be identified and generated based on an overall sound profile of the aerial vehicle, or on individual sounds emitted by the aerial vehicle by discrete sources.

Active noise cancellation techniques use an encoder to compress current reference conditions to a lower-dimensional latent space vector. The techniques also store a database of latent space vectors, which are representative of previously encountered reference conditions, and associated configuration parameters, such as filter coefficients/taps. Hence, when a vehicle transitions to a different condition (e.g., road condition) from a current condition, the system can match it with a previously encountered condition and quickly load corresponding configuration parameters for active noise cancellation.

An audio device is disclosed, comprising multiple microphones and an audio module. The multiple microphones generate multiple audio signals. The audio module coupled to the multiple microphones comprises a processor, a storage media and a post-processing circuit. The storage media includes instructions operable to be executed by the processor to perform operations comprising: producing multiple instantaneous relative transfer functions (IRTFs) using a known adaptive algorithm according to multiple spectral representations for multiple first sample values in current frames of the multiple audio signals; and, performing distractor suppression over the multiple spectral representations and the multiple IRTFs using an end-to-end neural network to generate a compensation mask. The post-processing circuit generates an audio output signal according to the compensation mask. Each IRTF represents a difference in sound propagation between each predefined microphone and a reference microphone of the microphones relative to sound sources.

Implementations of the subject technology provide systems and methods for determining whether to interrupt a user of an audio device that is operating in a noise-cancelling mode of operation. For example, the user may desire to be interrupted by one or more pre-designated contacts that are identified at an associated electronic device as interrupt-authorized contacts, or by a person who speaks a designated keyword to the user.

A method for actively monitoring sound emissions of turbomachinery, in particular turbomachinery which has an electric motor, preferably a ventilator or a turbomachine. A sound signal, which is produced by superimposing the sound emission of the turbomachinery with at least one counter sound signal, is captured by at least one receiver at at least one receiver position and is transmitted to a control unit, wherein the control unit has an artificial intelligence, and a control signal is generated by the artificial intelligence for at least one actuator while taking into consideration the sound signal such that the actuator generates a counter sound signal that interacts with the sound emission of the turbomachinery such that a sound load at least in the region of the receiver position or the receiver positions is reduced.

Disclosed herein is a magnetic resonance imaging system (100) controlled by a processor (130). Execution of machine executable instructions causes the processor to receive a selection input of gradient coil pulse commands, to provide the selected commands and at least one value relating to a further parameter to a trained machine learning system (122), to receive from the machine learning system information as to anti-noise to be generated by a sound transducer (124, 129) to compensate for noise experienced at the ears of a subject (118) in the magnetic resonance imaging system. The machine executable instructions further cause the processor to control the magnetic resonance imaging system with the pulse sequence commands and the set of gradient coil pulse commands for acquisition of the imaging k-space data and to synchronized therewith operate the sound transducer for generating anti-noise using the information as output by the trained machine learning system.

An active noise control system includes circuitry configured to perform independent component analysis when a level of a sound output from a microphone becomes greater than a predetermined level. In an independent component analysis process, by the independent component analysis, the circuitry separates a noise component from monitoring sound data that is output from the microphone, and stores data representing the noise component as statistical noise data. An adaptive filter in the active noise control system performs an adaptive operation to adapt an output of the microphone as an error, and outputs, as a noise cancellation sound from a speaker, a sound represented by noise cancellation sound data that is obtained by filtering the stored statistical noise data. The adaptive filter adapts, as an error, a filter coefficient used in filtering the monitoring sound data output from the microphone.