Nvidia patents audio enhancement using neural networks
Nvidia has been granted a patent for a method to improve audio quality by adding missing high-frequency details to sound signals. The system uses neural networks, specifically combining a gated recurrent unit and convolution layers, to predict and generate these additional frequencies from the original audio input.
In the filing’s own words
Apparatuses, systems, and techniques are presented to upsample audio. In at least one embodiment, one or more neural networks are used to determine one or more second frequencies of one or more audio signals based, at least in part, on only one or more first frequencies of the one or more audio signals.
What exactly they claim (claim 1)
1. A processor, comprising: one or more circuits to use one or more neural networks to generate one or more second frequencies of one or more audio signals based, at least in part, on one or more first frequencies of the one or more audio, wherein the one or more neural networks include a first path including a gated recurrent unit (GRU) neural network layer and a parallel, second path including one or more convolution layers.
Facts
- Company
- Nvidia (Nvidia Corporation)
- Official title
- Audio upsampling using one or more neural networks
- Patent number
- US12744049B2
- Application number
- 17470797
- Filed
- Sep 9, 2021
- Granted
- Sep 22, 2026
- Inventors
- 2
- Claims
- 31
Classified under
G10L 21/0324 Physics & computingG10L 25/30 Physics & computingMore from Nvidia in Audio & voice
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.