The inventive concept relates to a smart hearing device for providing a control parameter and feedback for a natural language or a non-natural language determined by analyzing sound data, which includes a receiving unit that receives sound data of a voice signal and a noise signal from a first microphone and a second microphone being formed at one side, a determination unit that compares digital flow of the sound data with a previously stored graph pattern to determine a natural language or a non-natural language for the sound data, a processing unit that matches similar data for the determined natural language or non-natural language, based on a database including a natural language area and a non-natural language area, and a providing unit that provides a user with a one-sided sound converted by setting a control parameter in a natural language or a non-natural language specified according to the matched similar data.

One example may include a method that includes receiving, at a presentation server, an audio data signal from a mobile device located in a presentation space, identifying a mobile device identification characteristic of the mobile device based on the received audio data signal, determining a mobile device location via a location determination procedure, and playing the audio signal via a loudspeaker.

A gaze direction of a user is determined by an eye-tracking system of a head mounted device. Audio data generated by at least one microphone is captured. Gaze-guided audio is generated from the audio data based on the gaze direction of the user.

A communication system with a noise cancellation (NC) assembly providing adaptive or dynamic noise cancellation. The NC assembly includes a localizer module determining, during a communication session (active speaking or during idle times), a location of the active talker. The NC assembly includes a beam generator forming a beam in the determined direction of the active talker to enhance the active talker speech. Once the NC assembly has determined the position of the active talker, the NC assembly assigns a microphone of the microphone array or generated beam in that active direction to be the “active signal” source. The NC assembly assigns a second microphone or beam to be the noise source for NC purposes, and this source may be selected to be in acoustic shadow of the first microphone used as the active signal source or may be the farthest away in its position from the active talker's position.

An audio capture device selects between multiple microphones to generate an output audio signal depending on detected conditions. The audio capture device determines whether one or more microphones are wet or dry and selects one or more audio signals from the one or more microphones depending on their respective conditions. The audio capture device generates a mono audio output signal or a stereo output signal depending on the respective conditions of the one or more microphones.

An electronic device may include at least one microphone, a speaker, and a processor operatively connected to the at least one microphone and the speaker, wherein the processor may be configured to configure an operation frequency of the microphone as a first frequency and receive an external audio signal from the outside of the electronic device through the microphone operating in the first frequency, generate a first audio signal using the received external audio signal, acquire noise signal information, based on the first audio signal, output a second audio signal generated based on the noise signal information through the speaker, determine a second frequency, based on the generated second audio signal, and change the operation frequency of the microphone to the second frequency and receive the external audio signal from the outside of the electronic device through the microphone operating at the second frequency.

An image capture device, having: a housing, a lens snout, a front microphone, a top microphone, and an audio processor. The housing has a top and front housing surface. The lens snout protrudes from the front housing surface. The front microphone mounted within or on the front housing surface and below the lens snout. The top microphone mounted within or on a top housing surface in a position biased toward the front housing surface. The audio processor comprises a memory that is configured to store instructions that when executed cause the audio processor to generate an output audio signal. The top microphone is located at a position to receive direct freestream air flow when the housing is positioned in a pitched forward orientation at a pitched forward angle relative to a vertical axis. The front microphone receives turbulent air flow from the lens snout when the housing is positioned in the pitched forward orientation.

A method of performing automatic speech recognition (ASR) using end-pointing markers generated using accelerometer-based voice activity detector starts with a voice activity detector (VAD) generating an accelerometer VAD output (VADa) based on data output by at least one accelerometer that is included in at least one earbud. The at least one accelerometer to detect vibration of the user's vocal chords. A voice processor detects a speech signal based on acoustic signals from at least one microphone. An end-pointer generates the end-pointing markers based on the VADa output and an ASR engine performs ASR on the speech signal based on the end-pointing markers. Other embodiments are also described.

A computer-implemented method, system and computer program product for detecting or predicting system faults in cooling systems. A model (deep learning model) is built and trained to detect or predict system faults in a cooling system based on acoustic emission signals (both in temporal and frequency domains) and/or imaging signals. Upon training the model to detect or predict system faults in a cooling system, acoustic emission signals may be obtained non-intrusively from the cooling system using acoustic emission sensors, hydrophones and/or microphones. Additionally, upon training the model to detect or predict system faults in a cooling system, imaging signals (e.g., boiling images) may be obtained non-intrusively from the cooling system using optical sensors (e.g., high-speed camera). The trained model may then detect or predict a system fault in the cooling system based on such information (acoustic emission signals, including in temporal and frequency domains, and/or the imaging signals).

An electronic apparatus includes an array of microphones for detecting audible sounds generated by a patient and for generating audio information representing the detected audible sounds, a first beamformer having a first adaptability speed and configured to generate first audio information and first noise information from the audio information, a second beamformer having a second adaptability speed which is slower than the first adaptability speed, the second adaptive beamformer configured to generate second audio information and second noise information from the audio information, an audio classification unit for generating audio classification information based on the first audio information, a head movement detection unit for generating head movement information based on at least one of the second audio information, the first noise information, and the second noise information, and a diagnosis unit for determining a sleep apnea diagnosis based on the audio classification information and the head movement information.