| CPC H04S 3/008 (2013.01) [G06F 3/162 (2013.01); H04S 7/305 (2013.01); H04R 2499/13 (2013.01); H04S 2400/01 (2013.01); H04S 2400/11 (2013.01)] | 6 Claims |
|
1. A method for converting a vehicle audio into a multi-channel surround sound, comprising:
acquiring multi-channel surround sound conversion parameters according to a parameter debugging step, the multi-channel surround sound conversion parameters comprising optimized audio channel equalization parameters and optimized sound mixing parameters corresponding to various spatial reverberation modes of a vehicle of a target model;
acquiring a target vehicle audio signal from a vehicle of a target model, and decoding the target vehicle audio signal to obtain target audio data in a standard format;
extracting features of the target audio data, the extracted features comprising time domain features and frequency domain features;
performing classification according to the extracted features by using an audio separation model, to separate the target audio data into a plurality of target single audio signals, different target single audio signals being located in different audio channels;
determining corresponding optimized audio channel equalization parameters and optimized sound mixing parameters according to a target spatial reverberation mode selected from the plurality of preconfigured spatial reverberation modes;
processing each target single audio signal located in each audio channel by using the optimized audio channel equalization parameters to obtain each equalized single audio signal;
mixing equalized single audio signals by using the optimized sound mixing parameters to obtain a result audio signal; and
outputting the mixed result audio signal;
wherein, the parameter debugging step comprises:
acquiring a vehicle audio signal for debugging from the vehicle of the target model, and decoding the vehicle audio signal for debugging to obtain audio data for debugging in a preset standard format;
extracting features of the audio data for debugging, the extracted features comprising time domain features and frequency domain features;
performing classification according to the extracted features by using an audio separation model, to separate the audio data for debugging into a plurality of single audio signals for debugging, different single audio signals for debugging being located in different audio channels;
determining surround sound channels of the vehicle sound system of the target model; selecting a matched sound mixing algorithm according to the surround sound channels; mixing the plurality of separated single audio signals for debugging by using a sound mixing algorithm, and recording parameters of current sound mixing algorithm as original sound mixing parameters;
pre-configuring a plurality of spatial reverberation modes, and debugging equalization parameters of the audio channels and the original sound mixing parameters for each spatial reverberation mode, comprising:
presetting various evaluation factors and corresponding weights for audio quality;
operating the vehicle sound system multiple times;
obtaining a score of each evaluation factor for each operation, and calculating a quality score of the operation in conjunction with the corresponding weights; and
performing a preset number of operations, and selecting equalization parameters of the audio channels and sound mixing parameters under an operation with a highest quality score as optimized audio channel equalization parameters and optimized sound mixing parameters corresponding to the spatial reverberation mode respectively; or stopping the operation of the vehicle sound system when the quality score reaches a preset optimization score threshold, and taking equalization parameters of the audio channels and sound mixing parameters under a last operation as the optimized audio channel equalization parameters and the optimized sound mixing parameters corresponding to the spatial reverberation mode respectively; and
determining and saving the optimized audio channel equalization parameters and optimized sound mixing parameters corresponding to each spatial reverberation modes as the multi-channel surround sound conversion parameters.
|