The present technology relates to a particular-sound detector and method, and a program that make it possible to improve the performance of detecting particular sounds. The particular-sound detector includes a particular-sound detecting section that detects a particular sound on a basis of a plurality of audio signals obtained by collecting sounds by a plurality of microphones provided to a wearable device. In addition, the plurality of the microphones includes two microphones that are equidistant at least from a sound source of the particular sound, and one microphone arranged at a predetermined position. The present technology can be applied to headphones.

For example, a controller of an Active Acoustic Control (AAC) system may be configured to process input information including AAC configuration information, and a plurality of noise inputs representing acoustic noise at a plurality of noise sensing locations. For example, the controller may be configured to process the input information to determine a sound control pattern to control sound within a sound control zone based on the plurality of noise inputs. For example, the controller may include a Neural-Network (NN) trained to generate an NN output based on an NN input, wherein the NN input is based on the AAC configuration information. For example, the controller may be configured to generate the sound control pattern based on the NN output, and to output the sound control pattern to one or more acoustic transducers.

The present technology relates to a particular-sound detector and method, and a program that make it possible to improve the performance of detecting particular sounds.

The particular-sound detector includes a particular-sound detecting section that detects a particular sound on a basis of a plurality of audio signals obtained by collecting sounds by a plurality of microphones provided to a wearable device. In addition, the plurality of the microphones includes two microphones that are equidistant at least from a sound source of the particular sound, and one microphone arranged at a predetermined position. The present technology can be applied to headphones.

A method for generating anti-noise comprises receiving a sound signal representative of ambient sound including noise from a noise source, anti-noise from an anti-noise generator, and propagation noise from environment; processing the sound signal using a deep learning algorithm configured to generate an anti-noise signal to form anti-noise; and outputting the anti-noise signal to the anti-noise generator. The deep learning algorithm features an iterative encoder module forming plural feature maps; an attention module generating plural attention maps respectively based on the feature maps; a recurrent neural network (RNN), with long short-term memory layers receiving the feature map of the final iteration of the encoder module, predicting a future portion of the sound signal and modelling temporal features of the feature map of the final encoder module iteration; and an iterative decoder module mapping the output of the RNN to the anti-noise signal having common dimensions as the sound signal.

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.

Disclosed in the present disclosure are an earphone and an audio processing method and apparatus therefor, and a storage medium. The audio processing method comprises: acquiring a bone conduction signal and a microphone signal when the earphones are in worn states; performing phase adjustment on the bone conduction signal to obtain an adjusted bone conduction signal; and inputting an audio stream, which contains the adjusted bone conduction signal and the microphone signal, into an audio playing unit of the earphones to play the audio stream, so that co-channel interference is generated between the adjusted bone conduction signal in the audio stream and a sound which is transmitted to an ear canal through a user's skeletons.

This disclosure provides systems, methods, and devices for audio signal processing that support feedback cancellation in a personal audio amplification system. In a first aspect, a method of signal processing includes receiving an input audio signal, wherein the input audio signal includes a desired audio component and a feedback component; and reducing the feedback component by applying a machine learning model to the input audio signal to determine an output audio signal. Other aspects and features are also claimed and described.

Embodiments of the present disclosure disclose an earphone including a fixing structure, a first microphone array, a processor, and a speaker. The fixing structure is configured to fix the earphone near a user's ear without blocking the user's ear canal and including a hook-shaped component and a body part. The first microphone array is located in the body part and is configured to pick up environmental noise. The processor is located in the hook-shaped component or the body part and is configured to estimate a sound field at a target spatial position using the first microphone array and generate a noise reduction signal based on the estimated sound field. The target spatial position is closer to the user's ear canal than any microphone in the first microphone array. The speaker is located in the body part and is configured to output a target signal according to the noise reduction signal.

For example, a controller of an Active Acoustic Control (AAC) system may be configured to process input information including AAC configuration information, and a plurality of noise inputs representing acoustic noise at a plurality of noise sensing locations. For example, the controller may be configured to process the input information to determine a sound control pattern to control sound within a sound control zone based on the plurality of noise inputs. For example, the controller may include a Neural-Network (NN) trained to generate an NN output based on an NN input, wherein the NN input is based on the AAC configuration information. For example, the controller may be configured to generate the sound control pattern based on the NN output, and to output the sound control pattern to one or more acoustic transducers.

Embodiments of the present disclosure set forth a method of reducing noise in an audio signal. The method includes determining, based on sensor data acquired from a first set of sensors, a first position of a user in an environment. The method also includes acquiring, via the first set of sensors, one or more audio signals associated with sound in the environment and identifying one or more noise elements in the one or more audio signals. The method also includes generating a first directional audio signal based on the one or more noise elements. When the first directional audio signal is outputted by a first speaker, the first speaker produces a first acoustic field that attenuates the one or more noise elements at the first position.