Disclosed herein are system, apparatus, article of manufacture, method, and/or computer program product embodiments for a mobile device based control device locator. An embodiment operates by receiving a request to locate a control device, transmitting acoustic token transmission information to the control device to activate an electroacoustic transducer on the control device, receiving an acoustic signal including an acoustic token signal from the control device via a plurality of acoustic sensors, and determining distance information of the control device based on the received acoustic token signal generated by the electroacoustic transducer of the control device.

Disclosed are techniques for a multimedia device with audio and video capturing capability to identify an audio device based on acoustic playback signal if the audio device cannot be identified from captured video. The multimedia device may assemble a list of candidate audio devices that are a possible match for the observed audio device from a database of previously recognized audio devices and may transmit commands to the candidate audio devices to play acoustic identification signals. The acoustic identification signals may be audible sound or ultrasonic tone sequences with embedded identification information unique to each audio device. The multimedia device may record and analyze the acoustic identification signals received from any of the candidate audio devices to construct metrics to select the most likely candidate for the observed audio device. The metrics may include time of flight, direction of arrival, received amplitude, direct-to-reverberant ratio (DRR) of the acoustic identification signals.

Techniques for audio tagging of an object of interest are provided. An object of interest within a field of view of a first video camera may be identified at a first time. At least one audio tag representing a first sound created by the object of interest may be generated and associated with the object of interest. At a second time later than the first and at a second video camera, a second sound generated by an unidentified object that is not in the field of view of the second video camera may be detected. An audio tag representing the second tag may be generated. It may be determined that the object of interest and the unidentified object of interest are the same when the audio tag representing the first sound and the second sound are the same.

A sound source separation system includes: a controller that: acquires pieces of sound collection data with microphones that collect sounds output from first and second sound sources. The first sound source is at a first position at which effective distances from the microphones are equal and the second sound source is at a different position. The controller further acquires, based on the sound collection data, frequency spectra in two dimensions of a circumferential direction of a circle and a time direction. The first position is a center of the circle and each of the effective distances is a radius of the circle. The controller further separates, from the frequency spectra, a first sound source spectrum and a second sound source spectrum.

Provided is a direction of arrival estimation device wherein: a calculation circuit calculates a frequency weighting factor for each of a plurality of frequency components of signals recorded in a microphone array, on the basis of the differences among unit vectors indicating the directions of the sound sources of each of the plurality of frequency components; and an estimation circuit estimates the direction of arrival of a signal from the sound source, on the basis of the frequency weighting factors.

A method of determining a distance between a vehicle and a sound source includes detecting, at a microphone of the vehicle, sounds from a sound source external to the vehicle. The sounds have a first frequency component at a first frequency and a second frequency component at a second frequency. The method also includes determining, at a processor of the vehicle, a classification of the sound source based on audio properties of the sounds. The method further includes determining a first energy level associated with the first frequency component and a second energy level associated with the second frequency component. The method also includes determining a ratio between the first energy level and the second energy level. The method further includes determining the distance between the vehicle and the sound source based on the ratio and the classification of the sound source.

Acoustic imaging systems can include an acoustic sensing array, an electromagnetic imaging tool, a display, and an audio device. A processor can receive data from the acoustic sensor array and the electromagnetic imaging tool to generate a display image combining acoustic image data and electromagnetic image data. Systems can include an audio device that receives an audio output from the processor and outputs audio feedback signals to a user. The audio feedback signals can represent acoustic signals from an acoustic scene. Systems can provide a display image to a user including acoustic image data, and a user can select an acoustic signal for which to provide a corresponding audio output to an audio device. Audio outputs and display images can change dynamically in response to a change in pointing of the acoustic sensing array, such as by changing a stereo audio output.

Acoustic imaging systems can include an acoustic sensing array, an electromagnetic imaging tool, a display, and an audio device. A processor can receive data from the acoustic sensor array and the electromagnetic imaging tool to generate a display image combining acoustic image data and electromagnetic image data. Systems can include an audio device that receives an audio output from the processor and outputs audio feedback signals to a user. The audio feedback signals can represent acoustic signals from an acoustic scene. Systems can provide a display image to a user including acoustic image data, and a user can select an acoustic signal for which to provide a corresponding audio output to an audio device. Audio outputs and display images can change dynamically in response to a change in pointing of the acoustic sensing array, such as by changing a stereo audio output.

A sound or vibration source localization system with a master unit and a plurality of slave units. The master unit transmit a time synchronization signal via an RF link to the slave units. A microphone or vibration sensor in each of the slave units are used to record a short time sequence, e.g. 0.2-2 seconds, of sound or vibration time aligned with the time synchronization signal to ensure synchronous recording of the time sequences at all slave units. The slave unit transmit the recorded time aligned time sequences via an RF link along with a time stamp and an identification code to the master unit. The master unit has a processor system arranged to process the received time sequences from the slave units according to a lizard ear mimicking algorithm. Such type of algorithm provides a good direction estimate in response to two input signals recorded at different positions, even with a short time sequence. As a result, and preferably along with information regarding physical positions of the slave units, a sound source or vibration source localization estimate can be generated.

A multi-microphone algorithm for detecting and differentiating interference sources from desired talker speech in advanced audio processing for smart home applications is described. The approach is based on characterizing a persistent interference source when sounds repeated occur from a fixed spatial location relative to the device, which is also fixed. Some examples of such interference sources include TV, music system, air-conditioner, washing machine, and dishwasher. Real human talkers, in contrast, are not expected to remain stationary and speak continuously from the same position for a long time. The persistency of an acoustic source is established based on identifying historically-recurring inter-microphone frequency-dependent phase profiles in multiple time periods of the audio data. The detection algorithm can be used with a beamforming processor to suppress the interference and for achieving voice quality and automatic speech recognition rate improvements in smart home applications.