SPEECH CODING AND DECODING METHOD USING A NEURAL NETWORK MODEL THAT RECOGNIZES SOUND SOURCES AND AN ENCODING AND DECODING APPARATUS THAT PERFORMS THE SAME

摘要

Disclosed are a method for encoding and decoding a voice signal using a neural network model for recognizing a sound source, and an encoding and decoding apparatus for performing the same. A method of encoding a voice signal according to an embodiment of the present invention includes: identifying input signals for a plurality of sound sources; encoding the input signal to generate a latent signal; obtaining a plurality of sound source signals by separating the latent signal for each of the plurality of sound sources; determining the number of bits used for quantization of each of the plurality of sound source signals according to the type of the sound source; quantizing each of the plurality of sound source signals according to the determined number of bits; and generating a bitstream by combining the plurality of quantized sound source signals.