Multi-channel signal encoding and decoding method and apparatus

A method comprising:

• obtaining first decoded group information of first M blocks of a first sound channel of a current frame of a multi-channel signal from a bitstream, wherein the first decoded group information indicates M first decoded transient identifiers of the first M blocks;
• obtaining second decoded group information of second M blocks of a second sound channel of the current frame, wherein the second decoded group information indicates M second decoded transient identifiers of the second M blocks;
• decoding the bitstream, using a decoding neural network, to obtain first decoded spectrums of the first M blocks and second decoded spectrums of the second M blocks;
• obtaining a first reconstructed signal of the first sound channel based on the first decoded group information and the first decoded spectrums;
• and
• obtaining a second reconstructed signal of the second sound channel based on the second decoded group information and the second decoded spectrums.

An apparatus comprising:

• a memory configured to store instructions;
• one or more processors coupled to the memory and configured to execute the instructions to cause the apparatus to:
• obtain M first transient identifiers of first M blocks of a first sound channel of a current frame of a multi-channel signal based on first spectrums of the first M blocks,
• wherein the first M blocks comprise a first block of the first sound channel, and wherein a first transient identifier of the first block indicates that the first block is transient or non-transient;
• obtain first group information of the first M blocks based on the M first transient identifiers;
• obtain M second transient identifiers of second M blocks of a second sound channel of the current frame based on second spectrums of the second M blocks, wherein the second M blocks comprise a second block of the second sound channel, and wherein a second transient identifier of the second block indicates that the second block is transient or non-transient;
• obtain second group information of the second M blocks based on the M second transient identifiers;
• obtain, when the first group information and the second group information meet a preset condition, first adjusted group information and second adjusted group information based on the first group information and the second group information, wherein the first adjusted group information corresponds to the first group information, wherein the second adjusted group information corresponds to the second group information, and wherein the first adjusted group information is same as the first group information, and the second adjusted group information is based on adjusting the second group information, the first adjusted group information is based on adjusting the first group information, and the second adjusted group information is same as the second group information, or the first adjusted group information is based on adjusting the first group information, and the second adjusted group information is based on adjusting the second group information;
• obtain a first to-be-encoded spectrum based on the first adjusted group information and the first spectrums;
• obtain a second to-be-encoded spectrum based on the second adjusted group information and the second spectrums;
• obtain the first to-be-encoded spectrum and the second to-be-encoded spectrum by using an encoding neural network to obtain a spectrum encoding result;
• and
• write the spectrum encoding result into a bitstream.