Sony Corporation

Sony Group Corporation

Sony Europe Limited

Fabien Cardinaux

Stefan Uhlich

Thomas Kemp

Michael Enenkl

Franck Giron

Marc Ferras Font

Patrick Putzolu

Andreas Schwager

Wilhelm Hagg

Aurel Bordewieck

Javier Alonso Garcia

Stephen Tiedemann

Kazuki Yoshiyama

Daavid Hentunen

Fritz Hohl

Olivier Demarto

Tom Cool

Lukas Mauch

Hugo Magalhaes

A method comprising a deep learning based translation system translating a source sentence from language A to a target sentence in language B, placing constraints on the target sentence in language B.

Electronic device, method and computer program

An apparatus comprising circuitry that implements an artificial neural network training algorithm that uses weight tying.

Apparatus and method for training neural networks using weight tying

An electronic device for a vehicle comprising circuitry configured to obtain information about a planned maneuver of the vehicle; and circuitry configured to determine the position and/or orientation of a sound field based on the information about the planned maneuver of the vehicle.

A computer-implemented method of training an artificial neural network (ANN) by generating a first learned parameter for use in normalising input data values during a subsequent inference phase of the trained ANN. The method includes, for each of a series of batches of training data values, deriving a batch variance of the batch of training data values and a running variance of all training data values already processed in the training phase; generating an approximation of a current value of the first learned parameter so that a first scaling factor dependent upon the approximation of the first learned parameter and the running variance, is constrained to be equal to a power of two; and normalizing the batch of input data values by a second scaling factor dependent upon the approximation of the current value of the first learned parameter and the batch variance.

Artificial neural network

It is disclosed a method comprising obtaining a target spectrum, obtaining a set of non-target spectra, the set of non-target spectra comprising one or more non-target spectra, summing the target spectrum and the set of non-target spectra to obtain a mixture spectrum, and training an artificial neural network by using the mixture spectrum as input of the neural network and by using a spectrum which is based on the target spectrum as desired output of the artificial neural network.

Method, system and artificial neural network

A method of providing information about a device is proposed. According to the method, user-specific information of a first user is provided to the device. The user-specific information is related to a user experience of the device used by the first user. The user-specific information is stored in a non-volatile memory of the device. Upon a request of a second user, device-specific information based on the stored user-specific feedback information from the non-volatile memory of the device is outputted to the second user. A device with an electrical circuit, non-volatile memory, and an output circuit is proposed.

Concepts of providing information about a device

An electronic device comprising circuitry configured to perform a transcript based voice enhancement based on a transcript to obtain an enhanced audio signal.

An electronic device comprising circuitry configured to obtain an audio signal of a first passenger of a vehicle and to control a loudspeaker array to generate at least one virtual sound source that reproduces the audio signal obtained from the first passenger, the virtual sound source being provided for a second passenger.

An apparatus comprising circuitry configured to generate one or more focused sound sources as virtual loudspeakers of an announcement system.

Apparatus, system, method and computer program for distributing announcement messages

A device for room geometry analysis comprising: a plurality of segments (-) built of acoustic metamaterials, each segment (&#x3c6;, &#x3b8;) acting as a waveguide with a unique transfer function (B(&#x3c6;, &#x3b8;, &#x3c9;)); and a processor configured to calculate delays (&#x3c4;(&#x3c6;, &#x3b8;)) and respective directions (c(&#x3c6;, &#x3b8;)) of mirror sound sources (-) by decomposing a sound signal (&#x15c;) obtained from a microphone () based on the transfer functions (B(&#x3c6;, &#x3b8;, &#x3c9;)) of the segments (-) and based on a calibration signal (tsp(t)) emitted by a speaker ().

Acoustic metamaterial device, method and computer program

The present disclosure relates to concepts of acoustic noise cancelling. A noise cancelling apparatus contains a propulsion component configured to autonomously move the noise cancelling apparatus, and circuitry. The circuitry is configured to determine a position of an acoustic source, to determine a position of an acoustic receiver, and, depending on the detected positions of the acoustic source and the acoustic receiver, to control the propulsion component to navigate the noise cancelling apparatus to a target position to at least partly cancel an acoustic signal from the acoustic source at the position of the acoustic receiver.

Apparatuses and methods for acoustic noise cancelling

An electronic device has a display and a circuitry. The circuitry is configured to obtain location information of a specific item of multiple items located in an environment, wherein the location information of the specific item is obtained based on a correlation between location tracking information of electronic devices moving in the environment and item list data representing items of the multiple items being purchased by users of the electronic devices for which the location tracking information has been provided; and display an indication of the location of the specific item on the display.

Electronic device, apparatus and system

A device for active noise control inside a vehicle, the device comprising a processor () configured to determine a noise wavefield within the vehicle based on noise signals captured by a microphone array (M-M); determine the position of the ears of a passenger (P) based on information obtained from a head tracking sensor (HTU); capture a noise field inside the vehicle based on information obtained by the microphone array; obtain a noise level at the ears of the passenger (P) from the noise field; and determine an anti-noise field based on the noise level at the position of the ears of the passenger.

Electronic device, method and computer program for active noise control inside a vehicle

In method the following is performed: receiving input audio content representing mixed audio sources; separating the mixed audio sources, thereby obtaining separated audio source signals and a residual signal; and generating output audio content by mixing the separated audio source signals and the residual signal.

Growing community of inventors

Stuttgart, Germany

Fabien Cardinaux