A method and apparatus for determining a direction of infrasound. Infrasound is received by a directional infrasound sensor comprising a plurality of channels and a plurality of sensor devices. Each channel in the plurality of channels comprises a single opening at a first end of the channel and a closed end opposite the opening. The opening of each channel in the plurality of channels is pointed in a different direction from the opening of each other channel in the plurality of channels. The plurality of sensor devices includes a sensor device at the closed end of each channel in the plurality of channels. Each sensor device in the plurality of sensor devices is configured to generate a sensor signal in response to pressure. The sensor signals generated by the plurality of sensor devices are processed to determine the direction of the infrasound received by the directional infrasound sensor.

Described herein are systems, methods, and non-transitory computer readable media for determining a direction of movement of an authority vehicle in relation to another vehicle such as an autonomous vehicle and initiating or ceasing a vehicle response measure that may have previously been initiated based on the determined direction of movement. A signal source associated with the authority vehicle emits a periodic acoustic signal that is received at one or more audio capture devices, which may be provided at various locations on an exterior of a vehicle. One or more signal characteristics of the acoustic signal can be determined such as frequency, sound intensity, and/or phase. Detected signal characteristic(s) of the acoustic signal can be analyzed, and in some cases, compared against known information such as an expected frequency of the acoustic signal to determine the direction of movement of the authority vehicle in relation to the vehicle.

An apparatus comprises a receiver (201) receiving a multi-channel audio signal representing audio for a scene. An extractor (203) extracts at least one directional audio component by applying a spatial filtering to the multi-channel signal where the spatial filtering is dependent on the multi-channel audio signal. A feature processor (205) determines a set of features for the first directional audio component and a categorizer (207) determines a first audio source category out of a plurality of audio source categories for the directional audio signal in response to the set of features. An assigner (209) assigns a first audio source property to the first directional audio component from a set of audio source properties for the first audio source category. The apparatus may provide very advantageous categorization and characterization of individual audio sources/components present in a multi-channel signal. This may be advantageous e.g. for visualization of audio events.

Computing devices and methods utilizing a joint speaker location/speaker identification neural network are provided. In one example a computing device receives an audio signal of utterances spoken by multiple persons. Magnitude and phase information features are extracted from the signal and inputted into a joint speaker location and speaker identification neural network. The neural network utilizes both the magnitude and phase information features to determine a change in the person speaking. Output comprising the determination of the change is received from the neural network. The output is then used to perform a speaker recognition function, speaker location function, or both.

A system may include a wearable apparatus dimensioned to be worn by a user about an axial region of the user’s body such that, when the wearable apparatus is worn by the user, the user’s field of view into a local environment is substantially free of a view of the wearable apparatus. The system may also include a machine-perception subsystem that is coupled to the wearable apparatus and that gathers information about the local environment by observing the local environment. Additionally, the system may include an experience-analysis subsystem that infers, based on the information about the local environment and information about the user, contextual information about an experience of the user in the local environment. Furthermore, the system may include a non-visual communication subsystem that outputs the contextual information about the experience of the user. Various other apparatuses, systems, and methods are also disclosed.

A system, article, and method of acoustic angle of arrival detection uses both same-time and delayed-time audio signal value comparisons in a time domain that are input to a classifier neural network.

Systems and methods are provided for sensing acoustic signals using a floating base vector sensor. A vector sensor according to an embodiment of the present disclosure can be used to detect and characterize low frequency sound wave(s) in a viscous medium (e.g., air, water, etc.) by detecting a periodic motion of the media particles associated with the sound wave(s). The orientation of the particle velocity deduced from such measurements can provide information regarding the wave vector of the sound wave(s), can define the direction of arrival (DOA) for the acoustic signal, and can assist locating the source of the sound of interest.

Systems and methods are provided for sensing acoustic signals using a floating base vector sensor. A vector sensor according to an embodiment of the present disclosure can be used to detect and characterize low frequency sound wave(s) in a viscous medium (e.g., air, water, etc.) by detecting a periodic motion of the media particles associated with the sound wave(s). The orientation of the particle velocity deduced from such measurements can provide information regarding the wave vector of the sound wave(s), can define the direction of arrival (DOA) for the acoustic signal, and can assist locating the source of the sound of interest.

A non-transitory computer-readable storage medium storing a program that causes a processor included in a computer mounted on a sound source direction estimation device to execute a process, the process includes calculating a sound pressure difference between a first voice data acquired from a first microphone and a second voice data acquired from a second microphone and estimating a sound source direction of the first voice data and the second voice data based on the sound pressure difference, outputting an instruction to execute a voice recognition on the first voice data or the second voice data in a language corresponding to the estimated sound source direction, and controlling a reference for estimating a sound source direction based on the sound pressure difference, based on a time length of the voice data used for the voice recognition based on the instruction and a voice recognition time length.

A method and apparatus for determining a direction of infrasound. Infrasound is received by a directional infrasound sensor comprising a plurality of channels and a plurality of sensor devices. Each channel in the plurality of channels comprises a single opening at a first end of the channel and a closed end opposite the opening. The opening of each channel in the plurality of channels is pointed in a different direction from the opening of each other channel in the plurality of channels. The plurality of sensor devices includes a sensor device at the closed end of each channel in the plurality of channels. Each sensor device in the plurality of sensor devices is configured to generate a sensor signal in response to pressure. The sensor signals generated by the plurality of sensor devices are processed to determine the direction of the infrasound received by the directional infrasound sensor.