AUDIO RECOGNITION METHOD AND SYSTEM
    7.
    发明公开

    公开(公告)号:EP3355302A1

    公开(公告)日:2018-08-01

    申请号:EP16848057.2

    申请日:2016-09-14

    发明人: DU, Zhijun

    IPC分类号: G10L15/02 G10L25/18 G10L25/54

    摘要: Audio recognition methods and systems are disclosed. An audio recognition method comprises: performing diffusion processing on a plurality of first feature points in a spectrogram of a to-be-recognized audio file to obtain a feature point map (S110); searching in a spectrogram of a target audio file to determine whether second feature points that respectively correspond to the diffused first feature points in the feature point map (S120) exist; and if yes, determining that the spectrogram of the to-be-recognized audio file is a part of the target audio file (S130). The method can improve the matching success rate of feature points in audio recognition.