| CPC G10L 19/24 (2013.01) [G06N 3/044 (2023.01); G06N 3/08 (2013.01); G10L 19/167 (2013.01); G10L 25/60 (2013.01); G10L 25/69 (2013.01)] | 17 Claims |

|
1. A method for training an encoding bit rate prediction model, performed by a computer device, the method comprising:
obtaining a sample audio feature parameter corresponding to each of sample audio frames in a first sample audio, further including obtaining an (i−1)th sample encoding bit rate corresponding to an (i−1)th sample audio frame;
performing encoding bit rate prediction on the sample audio feature parameter through an encoding bit rate prediction model, to obtain a sample encoding bit rate for each of the sample audio frames, further including:
performing encoding bit rate prediction on an ith sample audio feature parameter and the (i−1)th sample encoding bit rate through the encoding bit rate prediction model, to obtain an ith sample encoding bit rate corresponding to an ith sample audio frame, wherein i is an increasing integer and a value range thereof is 1<i≤N, N is a quantity of the sample audio frames, and N is an integer larger than 1;
performing audio encoding on the sample audio frames based on the corresponding sample encoding bit rates to generate sample audio data corresponding to the sample audio frames;
performing audio decoding on the sample audio data, to obtain a second sample audio corresponding to the sample audio data; and
training the encoding bit rate prediction model based on the first sample audio and the second sample audio until a sample encoding quality score reaches a target encoding quality score,
the sample encoding quality score being determined through the first sample audio and the second sample audio.
|