Audio coding using machine learning based linear filters and non-linear neural sources

A method of reconstructing one or more audio signals, the method comprising:

• generating, using a first neural network, an excitation signal for at least one sample of an audio signal at least in part by performing a non-linear operation based on one or more inputs to the first neural network, the excitation signal being configured to excite a learned linear filter;
• generating, using a second neural network, a parameter for the learned linear filter based on the at least one sample of the audio signal, the parameter specifying characteristics for application by the learned linear filter;
• and
• generating, using the parameter for the learned linear filter and the excitation signal, at least one sample of a reconstructed audio signal.

A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to:

• generate, using a first neural network, an excitation signal for at least one sample of an audio signal at least in part by performing a non-linear operation based on one or more inputs to the first neural network, the excitation signal being configured to excite a learned linear filter;
• generate, using a second neural network, a parameter for the learned linear filter based on the at least one sample of the audio signal, the parameter specifying characteristics for application by the learned linear filter;
• and
• generate, using the parameter for the learned linear filter and the excitation signal, at least one sample of a reconstructed audio signal.