18689053. AUDIO CODING USING MACHINE LEARNING BASED LINEAR FILTERS AND NON-LINEAR NEURAL SOURCES (QUALCOMM Incorporated)
Contents
AUDIO CODING USING MACHINE LEARNING BASED LINEAR FILTERS AND NON-LINEAR NEURAL SOURCES
Organization Name
Inventor(s)
Guillaume Konrad Sautiere of Amsterdam (NL)
Duminda Dewasurendra of San Diego CA (US)
Zisis Iason Skordilis of San Diego CA (US)
Vivek Rajendran of San Diego CA (US)
AUDIO CODING USING MACHINE LEARNING BASED LINEAR FILTERS AND NON-LINEAR NEURAL SOURCES
This abstract first appeared for US patent application 18689053 titled 'AUDIO CODING USING MACHINE LEARNING BASED LINEAR FILTERS AND NON-LINEAR NEURAL SOURCES
Original Abstract Submitted
Systems and techniques are described for coding audio signals. For example, a voice decoder can 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. The voice decoder can further generate, using the learned linear filter and the excitation signal, at least one sample of a reconstructed audio signal. For example, a second neural network can be used to generate coefficients for one or more learned linear filters, which receive as input the excitation signal generated by the first neural network trained to perform the non-linear operation.
