A separation unit separates voice signals of a plurality of channels into an incoming component in each incoming direction, a selection unit selects a statistic corresponding to an incoming direction of the incoming component separated by the separation unit from a storage unit which stores a predetermined statistic and a voice recognition model for each incoming direction, an updating unit updates the voice recognition model on the basis of the statistic selected by the selection unit, and a voice recognition unit recognizes a voice of the incoming component separated using the voice recognition model.

Systems and methods are disclosed for autonomous joint detection-classification of acoustic sources of interest. Localization and tracking from unmanned marine vehicles are also described. Based on receiving acoustic signals originating above or below the surface, a processor can process the acoustic signals to determine the target of interest associated with the acoustic signal. The methods and systems autonomously and jointly detect and classify a target of interest. A target track can be generated corresponding to the locations of the detected target of interest. A classifier can be used representing spectral characteristics of a target of interest.

A wireless transceiver including: an array of antennas; a plurality of transmit and receive path components; an array of microphones; a composite spatial diagnostic circuit and a rule execution circuit. The plurality of components form transmit and receive paths coupled to the array of antennas for processing wireless communications. The composite spatial diagnostic circuit couples to the array of antennas and to the array of microphones to successively sample respectively a WiFi environment and an acoustic environment surrounding the wireless transceiver and to determine from each set of WiFi and acoustic samples a composite spatial map of humans and wireless transceivers within the surrounding environment. The rule execution circuit executes an action proscribed by a selected rule when a related portion of the composite spatial map sampled by the composite spatial diagnostic circuit exhibits a correlation above a threshold amount with a spatial context condition associated with the selected rule.

A conference speech presentation system, a sound localization method and apparatus, a conference system and a pickup device. The method includes the following steps: collecting (S101) a multi-channel voice signal through a directional microphone array; determining (S103) a steering vector including phase information and amplitude information according to array shape information and microphone pointing direction information; determining (S105) sound direction information according to the steering vector and the voice signal. By adopting this processing mode, both the phase information and the amplitude information are considered when determining the steering vector, which can effectively improve the accuracy of sound localization.

A microphone assembly includes at least three microphones to capture an input audio signal; an audio signal processing unit for processing the input audio signals to generate an output audio signal with a directivity; an audio source direction estimation unit; and a control unit. The audio source direction estimation unit includes first and second direction of arrival estimation modules for estimating first and second angles of incidence between an audio source and first and second axes defined by first and second pairs of the microphones, respectively; and an elevation estimation module for estimating an angle of elevation of the audio source with regard to a microphone plane based on the estimated first angle of incidence and the estimated second angle of incidence. The control unit uses the estimated angle of elevation to control a directivity parameter of the audio signal processing unit.

A method for audio focusing is provided, the method comprising: receiving a multi-channel audio signal that represents sounds in sound directions that correspond to respective positions in an image area of an image; receiving an indication of an audio focus direction that corresponds to a first position in the image area; selecting a primary sound direction from a plurality of different available candidate directions, wherein said plurality of different available candidate directions comprise said audio focus direction and one or more offset candidate directions and wherein each offset candidate direction corresponds to a respective candidate offset from said first position in the image area; and deriving, based on said multi-channel audio signal in dependence of the selected primary sound direction, an output audio signal.

Aspects of embodiments pertain to systems for estimating direction of arrival and delays of reflected and non-reflected sources in a room received by a plurality of sound capturing devices in the room, comprising obtaining sound data descriptive of received sources. Embodiments may further comprise determining, based on the sound data, a correlation value between each two audio channels of a plurality of audio channels to obtain, for a same frequency of the plurality of frequencies, a set of correlation values; and to perform a transform on each set of frequency-related correlation values to obtain a plurality of subsets of delay representations of a 3D Matrix. Each set of time delay representations may be analyzed or processed to extract information about the sources.

A method for mapping a source location by an electronic device is described. The method includes obtaining sensor data. The method also includes mapping a source location to electronic device coordinates based on the sensor data. The method further includes mapping the source location from electronic device coordinates to physical coordinates. The method additionally includes performing an operation based on a mapping.

A signal processor for processing target echo signal is provided. The signal processor includes a filter configured to generate a filtered echo signal by extracting echo signal components within a predetermined frequency band from the target echo signal, a high resolution signal generator configured to generate a high resolution signal based on the target echo signal, and a synthesizing module configured to synthesize the filtered echo signal with the high resolution signal. The high resolution signal has higher resolution than the filtered echo signal.

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.