The invention discloses an audio recognition method, an audio recognition device, a vehicle, computer equipment and a medium. The method comprises the following steps: encoding an audio to be identified to generate a pronunciation probability matrix; performing error correction on the pronunciation probability matrix through a preset delay error correction model to obtain a corresponding word result and an output probability matrix; performing pronunciation mapping on the word result and the output probability matrix to obtain a mapping probability matrix, and generating a target probability matrix according to the mapping probability matrix and the pronunciation probability matrix; and inputting the target probability matrix into the voice decoding graph for decoding so as to obtain a recognition result. Error correction is carried out on the pronunciation probability matrix through the error correction capability of the delay error correction model, so that an accurate word result is obtained, the accuracy of audio recognition is improved, and the delay error correction model can effectively save computing power, save storage space and the like.

    本申请公开一种音频识别方法、音频识别装置、车辆、计算机设备和介质。方法包括:对待识别音频进行编码,以生成发音概率矩阵;通过预设的延迟纠错模型,对发音概率矩阵进行纠错,以得到对应的字结果和输出概率矩阵;对字结果和输出概率矩阵进行发音映射,以得到映射概率矩阵,并根据映射概率矩阵和发音概率矩阵,生成目标概率矩阵;对目标概率矩阵输入到语音解码图进行解码,以得到识别结果。通过延迟纠错模型具备的纠错能力,对发音概率矩阵进行纠错,从而获取到准确的字结果,提高音频识别的准确性,且延迟纠错模型可以有效地节省算力,节省存储空间等。


    Access

    Download


    Export, share and cite



    Title :

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


    Additional title:

    音频识别方法、音频识别装置、车辆、计算机设备和介质


    Contributors:
    ZHANG LIAO (author) / YU XIAOJIE (author)

    Publication date :

    2024-01-26


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G10L Analyse oder Synthese von Sprache , SPEECH ANALYSIS OR SYNTHESIS / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion



    AUDIO-VISUAL AND COOPERATIVE RECOGNITION OF VEHICLE

    HASSNAA MOUSTAFA / SATHISH KUMAR KUTTAN / YING WEI LIEW et al. | European Patent Office | 2022

    Free access

    Audio transmission method, device and equipment, computer readable storage medium and vehicle

    LING HEPING / TIAN GUO / LI LI et al. | European Patent Office | 2024

    Free access

    Audio processing device, vehicle, audio processing method, and computer program product

    WANG CHENGWU / YUAN QUAN | European Patent Office | 2024

    Free access

    AUDIO RECOGNITION OF TRAFFIC PARTICIPANTS

    SCHEIBEL JÖRG / ZAGROBA JOSEPH | European Patent Office | 2021

    Free access

    Vehicle audio control method, vehicle audio device and vehicle

    WANG WENQIANG / ZHOU WENSHENG / SUN LINYAN et al. | European Patent Office | 2021

    Free access