Jump to content

Deepmind technologies limited (20250022476). BANDWIDTH EXTENSION OF INCOMING DATA USING NEURAL NETWORKS

From WikiPatents

BANDWIDTH EXTENSION OF INCOMING DATA USING NEURAL NETWORKS

Organization Name

deepmind technologies limited

Inventor(s)

Ioannis Alexandros Assael of London GB

Thomas Chadwick Walters of Bromley GB

Archit Gupta of Sunnyvale CA US

Brendan Shillingford of London GB

BANDWIDTH EXTENSION OF INCOMING DATA USING NEURAL NETWORKS

This abstract first appeared for US patent application 20250022476 titled 'BANDWIDTH EXTENSION OF INCOMING DATA USING NEURAL NETWORKS

Original Abstract Submitted

methods, systems, and apparatus, including computer programs encoded on computer storage media, for bandwidth extension. one of the methods includes obtaining a low-resolution version of an input, the low-resolution version of the input comprising a first number of samples at a first sample rate over a first time period; and generating, from the low-resolution version of the input, a high-resolution version of the input comprising a second, larger number of samples at a second, higher sample rate over the first time period. generating the high-resolution version includes generating a representation of the low-resolution version of the input; processing the representation of the low-resolution version of the input through a conditioning neural network to generate a conditioning input; and processing the conditioning input using a generative neural network to generate the high-resolution version of the input.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.