Spotify Ab

David Rubinstein

Peter Milan Thomson Sobot

Andreas Jansson

Angus William Sackfield

Ching Chuan Sung

Andreas Simon Thore Jansson

A system and method for controlling access to an on-device machine learning model without the use of encryption is described herein. For example, a request is received from an application executing on a device of a user. The request is to download a machine learning model to the device that enables a feature of the application, and the request includes information associated with the user and/or the device. The information is used to create an obfuscation key, and a derivative model can be generated using a reference copy of the machine learning model and the obfuscation key. The derivative model and the obfuscation key are then sent to the application. When the obfuscation key is provided to the derivative model at runtime, values derived from the obfuscation key are provided as additional inputs that enable the derivative model to function properly.

Access control for on-device machine learning models

An electronic device modifies a first media content item by superimposing a first set of data over a first accented musical event. The first accented musical event has a first audio profile. The first set of data has a second audio profile configured to be masked by the first audio profile during playback of the first media content item. The electronic device transmits, to a second electronic device, the modified first media content item.

Systems and methods for embedding data in media content

A system, method and computer product for estimating a component of a provided audio signal. The method comprises converting the provided audio signal to an image, processing the image with a neural network trained to estimate one of vocal content and instrumental content, and storing a spectral mask output from the neural network as a result of the image being processed by the neural network. The neural network is a U-Net. The method also comprises providing the spectral mask to a client media playback device, which applies the spectral mask to a spectrogram of the provided audio signal, to provide a masked spectrogram. The media playback device also transforms the masked spectrogram to an audio signal, and plays back that audio signal via an output user interface.

Singing voice separation with deep U-Net convolutional networks

An electronic device determines a first audio event of a first media content item and modifies the first media content item by superimposing a first set of data that corresponds to the first media content item over the first audio event. The first audio event has a first audio profile configured to be presented over a first channel for playback. The first set of data has a second audio profile configured to be presented over the first channel for playback. Playback of the second audio profile is configured to be masked by the first audio profile during playback of the first media content item. The electronic device transmits, to a second electronic device, the modified first media content item.

Growing community of inventors

New York, NY, United States of America

David Rubinstein