Patent · US Active

Using a predictive model to automatically enhance audio having various audio quality issues

US11514925B2 · kind B2 · utility

6Cited by
0References
20Claims
0Family size

Assignees

Inventors

Key dates

Filing dateApr 30, 2020
Grant dateNov 29, 2022
Priority date
Expiry dateJan 1, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2021/02082
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Operations of a method include receiving a request to enhance a new source audio. Responsive to the request, the new source audio is input into a prediction model that was previously trained. Training the prediction model includes providing a generative adversarial network including the prediction model and a discriminator. Training data is obtained including tuples of source audios and target audios, each tuple including a source audio and a corresponding target audio. During training, the prediction model generates predicted audios based on the source audios. Training further includes applying a loss function to the predicted audios and the target audios, where the loss function incorporates a combination of a spectrogram loss and an adversarial loss. The prediction model is updated to optimize that loss function. After training, based on the new source audio, the prediction model generates a new predicted audio as an enhanced version of the new source audio.

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