Apparatus and method for improving codec compression efficiency using artificial intelligence technology

摘要

The present embodiments provide a method for improving codec compression efficiency performed by a computing device including one or more processors and a memory for storing one or more programs executed by the processor, converting characteristics of an original signal according to input voice or audio to generate a low-resolution signal, encoding and decoding a low-resolution signal through a standard codec and codec simulating module to generate a distorted signal, and post-processing the distorted signal to restore the resolution of the input original signal and restore it Codec compression efficiency, characterized in that it is implemented to learn in an end-to-end method based on a deep learning network structure so that the codec simulation module plays a role similar to a standard codec Suggest ways to improve.