Perceptually-based loss functions for audio encoding and decoding based on machine learning
AssigneeDolby Laboratories Licensing Corporation
InventorsRoy M. FEJGIN, Grant A. DAVIDSON, Chih-Wei WU, Vivek KUMAR
Life of this patent
Estimating the term…
Loading patent…
AssigneeDolby Laboratories Licensing Corporation
InventorsRoy M. FEJGIN, Grant A. DAVIDSON, Chih-Wei WU, Vivek KUMAR
Estimating the term…
Computer-implemented methods for training a neural network, as well as for implementing audio encoders and decoders via trained neural networks, are provided. The neural network may receive an input audio signal, generate an encoded audio signal and decode the encoded audio signal. A loss function generating module may receive the decoded audio signal and a ground truth audio signal, and may generate a loss function value corresponding to the decoded audio signal. Generating the loss function value may involve applying a psychoacoustic model. The neural network may be trained based on the loss function value. The training may involve updating at least one weight of the neural network.
A computer-implemented method for training an autoencoder neural network implemented via a control system comprising one or more processors and one or more non-transitory storage media, comprising:
Dependencies are inferred from the claim text.