The invention relates to hydroacoustics and more specifically to hydroacoustic devices comprising, disposed in a single housing, a converter of liquid-medium oscillations and electrical signals, capable of receiving and/or transmitting hydroacoustic signals, the converter being disposed on a board which is connected to a switch cable for providing power and transmitting electrical signals, and may be used as a receiver and/or transmitter of hydroacoustic signals in water. According to the invention, the housing of the to hydroacoustic device is formed by the outer surfaces of the converter and board, and by a protective material which coats all of said surfaces, said material allowing for a transmission of hydroacoustic oscillations and being capable of transitioning from a highly-elastic or viscous-flow state to a solid state. The achieved technical result consists in simplifying the design of the device.

Provided is a source localization in an apparatus for performing a source localization, a target sound source enhancement or speech recognition. The source localization method using input signals input from a plurality of microphones, comprising steps of: (a) obtaining a log likelihood function or an auxiliary function under the assumption that a target source signal mixed with noises satisfies a CGMM model; (b) obtaining an equation for estimating parameter values of the log likelihood function or the auxiliary function so that a value of the log likelihood function or the auxiliary function is maximized recursively in each time frame; (c) estimating a covariance matrix recursively in each time frame; and (d) estimating a steering vector recursively by using the estimated covariance matrix, wherein the steering vector of the target sound source is estimated from the input signals.

The disclosure generally relates to a method, apparatus and system to deploy aquatic sensors to obtain oceanographic data. In an exemplary embodiment, a free-floating or untethered sensor receives signals from different transmitters. The signals may be configured to travel through air and/or water. The sensor records each signals' time of arrival and determines its location in relationship to known transmitters based on the signal travel time. The position of each sensor may be determined by triangulation to several devices whose positions are known. The distances from the sensor in question to each device is measured by means of time-of-flight measurements for a wireless signal from the sensor to each known-position device. Other methods such as trilateration or dead-reckoning may also be used. The sensor may additionally collect and record oceanographic or other environmental data.

Architectures and techniques to visually indicate an operational state of an electronic device. In some instances, the electronic device comprises a voice-controlled device configured to interact with a user through voice input and visual output. The voice-controlled device may be positioned in a home environment, such as on a table in a room of the environment. The user may interact with the voice-controlled device through speech and the voice-controlled device may perform operations requested by the speech. As the voice-controlled device enters different operational states while interacting with the user, one or more lights of the voice-controlled device may be illuminated to indicate the different operational states.

A speech recognition method acquires sound information via multiple microphones, detects a sound source interval including sound from the sound information, acquires an estimated direction of speech by conducting direction estimation on a speech interval from among the sound source interval, conducts an adaptation process of using the sound information to estimate filter coefficients, decides a buffer size of the sound information to hold in a buffer, based on sound source interval information, estimated direction information, and adaptation process convergence state information, holds the sound information in the buffer according to the buffer size, conducts a beamforming process using the sound information held in the buffer and the filter coefficients to acquire speech information, and conducts speech recognition on the speech information acquired by the beamforming process. The method decides the buffer size to be a size sufficient for convergence of the adaptation process immediately after sound information processing starts.

An electronic device and a voice processing method of the electronic device are provided. The electronic device includes a microphone array including a plurality of microphones facing specified directions; a sensor module configured to sense a user located near the electronic device; and a processor configured to select one of a plurality of users sensed near the electronic device, process a voice received from a direction in which the selected user is located, as a user input, and process a voice received from another direction, as noise.

There is provided a safety method of detecting and signaling presence of a danger related to a danger source, the method comprising providing a base station at the danger source comprising first detectors and second detectors, the base station being adapted to determine an angular position of a target detected by a first detector among the first detectors within a detection zone based on an angular orientation of the first detector known a priori by the base station, and to determine a distance of the target by activating a second detector among the second detectors to measure the distance between the target and the base station in response to the target detection; and providing targets with portable target devices adapted to send signals in response to signals received from the first detectors of the base station. The first detectors are radio frequency transceivers and the second detectors are ultrasound transceiver. There is also provided a safety system for detecting and signaling presence of a target in danger zone.

There is provided a safety method of detecting and signaling presence of a danger related to a danger source, the method comprising providing a base station at the danger source comprising first detectors and second detectors, the base station being adapted to determine an angular position of a target detected by a first detector among the first detectors within a detection zone based on an angular orientation of the first detector known a priori by the base station, and to determine a distance of the target by activating a second detector among the second detectors to measure the distance between the target and the base station in response to the target detection; and providing targets with portable target devices adapted to send signals in response to signals received from the first detectors of the base station. The first detectors are radio frequency transceivers and the second detectors are ultrasound transceiver. There is also provided a safety system for detecting and signaling presence of a target in danger zone.

A system which tracks a social interaction between a plurality of participants, includes a fixed beamformer that is adapted to output a first spatially filtered output and configured to receive a plurality of second spatially filtered outputs from a plurality of steerable beamformers. Each steerable beamformer outputs a respective one of the second spatially filtered outputs associated with a different one of the participants. The system also includes a processor capable of determining a similarity between the first spatially filtered output and each of the second spatially filtered outputs. The processor determines the social interaction between the participants based on the similarity between the first spatially filtered output and each of the second spatially filtered outputs.

Techniques are disclosed for scene analysis including the use of acoustic imaging and computer audio vision processes for monitoring applications. In some embodiments, an acoustic image device is utilized with a microphone array, image sensor, acoustic image controller, and a controller. In some cases, the controller analyzes at least a portion of the spatial spectrum within the acoustic image data to detect sound variations by identifying regions of pixels having intensities exceeding a particular threshold. In addition, the controller can detect two or more co-occurring sound events based on the relative distance between pixels with intensities exceeding the threshold. The resulting data fusion of image pixel data, audio sample data, and acoustic image data can be analyzed using computer audio vision, sound/voice recognition, and acoustic signature techniques to recognize/identify audio and visual features associated with the event and to empirically or theoretically determine one or more conditions causing each event.