The invention provides an audio signal processing method, device and equipment, a vehicle and a medium, and the method comprises the steps: collecting sound signals of a plurality of target environment sound regions through a plurality of vehicle-mounted pickup devices, and obtaining a plurality of paths of audio signals comprising a near-end voice signal and an echo signal; obtaining an echo reference signal, and inputting the multiple paths of audio signals and the echo reference signal into a trained audio signal processing model to obtain multiple paths of target voice signals corresponding to each target environment sound area; the audio signal processing model is obtained through supervised training based on multiple paths of audio sample signals; the audio sample signal is obtained by mixing a human voice sample signal and an echo reference sample signal; the sample label corresponding to each path of audio sample signal is a pure human voice signal. According to the embodiment of the invention, the pre-trained audio signal processing model is utilized to perform echo cancellation processing and sound area separation processing on the multiple paths of audio signals, so that the accuracy of voice signal output by each sound area can be improved.

    本公开提供了一种音频信号处理方法、装置、设备、车辆以及介质,所述方法包括:通过多个车载拾音装置对多个目标环境音区的声音信号进行采集,得到包括近端语音信号和回声信号的多路音频信号;获取回声参考信号,将多路音频信号和回声参考信号输入至训练好的音频信号处理模型中,得到与各个目标环境音区对应的多路目标语音信号;音频信号处理模型基于多路音频样本信号经有监督训练得到;音频样本信号为人声样本信号与回声参考样本信号混合得到的;每路音频样本信号对应的样本标签为纯净人声信号。本公开实施例利用预先训练好的音频信号处理模型对多路音频信号进行回声消除处理以及音区分离处理,进而可以提升各个音区输出语音信号的的准确性。


    Access

    Download


    Export, share and cite



    Title :

    Audio signal processing method, device and equipment, vehicle and storage medium


    Additional title:

    音频信号处理方法、装置、设备、车辆以及存储介质


    Contributors:
    ZHANG PENG (author) / YANG ZIYE (author) / FANG XIANGYANG (author) / HOU RUI (author)

    Publication date :

    2024-02-27


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS / B60R Fahrzeuge, Fahrzeugausstattung oder Fahrzeugteile, soweit nicht anderweitig vorgesehen , VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR




    Vehicle audio control method, electronic equipment and storage medium

    WANG LEI | European Patent Office | 2023

    Free access

    Vehicle-mounted audio output method and device, equipment and storage medium

    DENG XIN | European Patent Office | 2023

    Free access

    Audio recognition method, audio recognition device, vehicle, computer equipment and medium

    ZHANG LIAO / YU XIAOJIE | European Patent Office | 2024

    Free access

    Vehicle USB audio playing method and device, electronic equipment and storage medium

    ZENG YONGGANG / HE GANG / WANG HONGBO et al. | European Patent Office | 2023

    Free access