Patent · US Active

Method and system for real-time and low latency synthesis of audio using neural networks and differentiable digital signal processors

US12283284B2 · kind B2 · utility

0Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 19, 2022
Grant dateApr 22, 2025
Priority date
Expiry dateMay 19, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L25/90
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Example aspects include techniques for implementing real-time and low-latency synthesis of audio. These techniques may include generating a frame by sampling audio input in increments equal to a buffer size of until a threshold corresponding to a frame size used to train a machine learning (ML) model is reached, detecting feature information within the frame, determining, by the ML model, control information for audio reproduction based on the feature information. In addition, the techniques may include generating filtered noise information by inverting the noise magnitude control information using an overlap and add technique, generating, based on the control information, additive harmonic information by combining a plurality of scaled wavetables, and rendering audio output based on the filtered noise information and the additive harmonic information.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.