A method for voice recording and an electronic device thereof are provided. The method includes determining a voice recording mode from among a plurality of voice recording modes, determining a voice beamforming direction according to the determined voice recording mode, and recording voice signals based on the determined voice beamforming direction.

A system and method for processing user speech commands in a voice interactive system is disclosed. Users issue speech phrases on a local device in a premises network, and the local devices first determine if the speech phrases match any commands in a set of local control commands. The control commands, in examples, can activate and deactivate premises devices such as smart televisions and simpler lighting devices connected to home automation hubs. In the event of a command match, local actions associated with the commands are executed directly on the premises devices in response. When no match is found on the local device, the speech phrases are sent in messages to a remote server over a network cloud such as the Internet for further processing. This can save on bandwidth and cost as compared to current voice recognition systems.

Multiple Holocam Orbs observe a real-life environment and generate an artificial reality representation of the real-life environment. Depth image data is cleansed of error due to LED shadow by identifying the edge of a foreground object in an (near infrared light) intensity image, identifying an edge in a depth image, and taking the difference between the start of both edges. Depth data error due to parallax is identified noting when associated text data in a given pixel row that is progressing in a given row direction (left-to-right or right-to-left) reverses order. Sound sources are identified by comparing results of a blind audio source localization algorithm, with the spatial 3D model provided by the Holocam Orb. Sound sources that corresponding to identifying 3D objects are associated together. Additionally, types of data supported by a standard movie data container, such as an MPEG container, is expanding to incorporate free viewpoint data (FVD) model data. This is done by inserting FVD data of different individual 3D objects at different sample rates into a single video stream. Each 3D object is separately identified by a separately assigned ID.

A sound source localization apparatus is provided which can more surely detect a sound source located in a detection target region. The sound source localization apparatus includes a plurality of microphones and a baffle. The baffle has a first surface and a second surface. The second surface is a surface opposite to the first surface. The plurality of microphones are two-dimensionally arrayed and fixed in the first surface. The baffle allows the plurality of microphones to pick up direct sound arriving at the first surface and prevents the plurality of microphones from picking up direct sound arriving at the second surface.

An aspect of the invention is directed to a system of both atmospheric and underwater sensors for measuring pressure waves from a noise source. A system of pressure sensors can be formed to determine the location of an external noise source, whether in air or underwater. The system includes at least two arrays consisting of pressure sensors, including at least one atmospheric pressure sensor and at least one underwater pressure sensor, such as a hydrophone. Each sensor may be a seven-fiber intensity modulated fiber optic pressure sensor. The system includes an analog to digital converter for digitizing the pressure data received from each sensor and a processor which processes the received signals to calculate an approximate location of the noise source based upon the pressure signals received by the sensors at different times of arrival. The system can provide this capability in remote applications due to its low power requirements.

Range to a human speaker is determined using a laser-based time of flight (ToF) system, with the range then being used to adjust the gain of a microphone receiving the speaker's voice. If desired, an acoustic-based Direction of Arrival (DoA) system uses acoustic information to determine the direction of incoming sound, such as a person talking, and the direction of the sound is then used to focus the area of laser illumination.

A sound direction estimation device includes a transfer function storage unit configured to store transfer functions of sound sources in correlation with directions of the sound sources, a calculation unit configured to calculate the number of classes to be searched and a search interval for each class based on a desired search range and a desired spatial resolution for searching for the directions of the sound sources, and a sound source localization unit configured to search the search range for every search interval using the transfer function, to estimate the direction of the sound source based on the search result, to update the search range and the search interval based on the estimated direction of the sound source until the number of classes calculated by the calculation unit is reached, and to estimate the direction of the sound source.

Disclosed are a method of providing sound tracking information, a sound tracking apparatus for vehicles and a vehicle having the sound tracking apparatus. The method of providing sound tracking information includes generating sound tracking results based on sound data generated by sensing sound generated around a vehicle, calculating 3D coordinates of a target sound source according to angle values of the target sound source recognized from the sound tracking results, and generating a notification of the target sound source based on the 3D coordinates, and the sound tracking results include information on probabilities that an object corresponding to the target sound source is present at respective angles in each of continuous frames according to time.

A method for voice recording and an electronic device thereof are provided. The method includes determining a voice recording mode from among a plurality of voice recording modes, determining a voice beamforming direction according to the determined voice recording mode, and recording voice signals based on the determined voice beamforming direction.

The present invention includes methods, circuits, devices, systems and associated computer executable code for acquiring, processing and rendering acoustic signals. According to some embodiments, one or more direction specific audio signals may be generated using a microphone array comprising two or more microphones and an audio stream generator. The audio stream generator may receive a direction parameter from an optical tracking system. There may be provided an audio rendering system adapted to normalize and/or balance acoustic signals acquired from a soundscape.