Sony Corporation

Sony Group Corporation

Sony Semiconductor Solutions Corporation

Sony Europe Limited

Stefan Uhlich

Thomas Kemp

Fabien Cardinaux

Michael Enenkl

Marc Ferras Font

Franck Giron

Patrick Putzolu

Andreas Schwager

Wilhelm Hagg

Aurel Bordewieck

Nabil Sven Loghin

Stephen Tiedemann

Ben Eitel

Javier Alonso Garcia

Yuhki Mitsufuji

Thomas Handte

Dana Ciochina

Felix Fellhauer

Fritz Hohl

Altfried Dilly

Kazuki Yoshiyama

Fares Zenaidi

Giorgio Fabbro

Falk-Martin Hoffmann

Xin Guo

Naoya Takahashi

Rana Ahmed Salem

Bi Wang

Lev Markhasin

Sebastian Klenk

Julian Zinsser

Lukas Mauch

Kit Lam Lee

An electronic device comprising circuitry configured to separate by audio source separation a first audio input signal into a first vocal signal and an accompaniment, and to transpose an audio output signal by a transposition value based on a pitch ratio, wherein the pitch ratio is based on comparing a first pitch range of the first vocal signal and a second pitch range of the second vocal signal.

Audio transposition

An electronic device having a circuitry configured to perform audio source separation on an audio input signal to obtain a separated source and configured to perform audio dubbing on the separated source based on replacement conditions to obtain a personalized separated source.

Audio source separation and audio dubbing

An electronic device having circuitry, which is configured to estimate a distraction level of an audio object stream, and to modify the audio object stream based on the estimated distraction Audio object level to obtain a modified audio object stream.

Electronic device, method and computer program

An image processing circuitry configured to: store, based on an obtained command, a first image identifier of first image data or the first image data on a write-once-read-many memory, wherein the first image identifier is generated based on the first image data such that it is unique for the first image data.

Image processing circuitry and image processing method

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.

According to an aspect of the present disclosure there is provided a communication device comprising circuitry configured to modulate a four-dimensional input signal by combining the four real-valued signal components of the input signal into a transformed signal and multiplying the transformed signal by carrier signals using two different carrier frequencies to obtain a transmit signal, and transmit the transmit signal.

Communication devices and methods

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

An electronic device comprising a circuitry configured to perform () blind source separation () based on a received input signal () to obtain separated sources; to perform () time-domain filtering () on at least one of the separated sources to obtain at least one filtered separated source; and to perform () remixing or upmixing () based on the at least one filtered separated source.

Device, method and computer program for blind source separation and remixing

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

An electronic device comprising circuitry configured to perform () source separation () based on a received audio input to obtain a separated source, to perform onset detection () on the separated source to obtain an onset detection signal and to mix () the audio signal with the separated source based on the onset detection signal to obtain an enhanced separated source.

The improved beamforming devices for communication systems operating in the mm-wave spectrum are particularly designed for antenna architectures consisting of antenna arrays, comprising multiple antenna array elements. The disclosed approaches comprise intelligent two stage searches, wherein information from the first stage is used in the second stage. This significantly reduces the computational complexity compared to the known approaches, with minimal loss in performance.

Beamforming device for antenna arrays

An electronic device, including an input interface configured to receive an input signal, a command determination unit configured to determine a plurality of possible commands based on the input signal, and an output interface configured to provide a plurality of output information corresponding to effects associated with each of the plurality of determined possible commands.

Growing community of inventors

Stuttgart, Germany

Stefan Uhlich