Infant sound detection method and device and storage medium

The invention discloses a baby sound detection method and device and a storage medium. The method comprises the following steps: acquiring an audio clip; according to the load condition of the current computing resource, performing buffering processing on the audio clip to obtain a cached audio clip; performing crying detection according to the cached audio clip, and storing a detection result in a detection queue; and performing voting processing according to multiple detection results in the detection queue to obtain a final detection result. According to the invention, the audio data is buffered by considering the load condition of the current computing resource, so that the detection accuracy can be improved. The method can be widely applied to the technical field of infant sound analysis. 本发明公开了一种婴儿声音检测方法、装置和存储介质，其中方法包括以下步骤：获取音频片段；根据当前计算资源的负载情况，对所述音频片段进行缓冲处理，获得缓存音频片段；根据所述缓存音频片段进行啼哭检测，并将检测结果保存至检测队列；根据检测队列中的多次检测结果进行投票处理，获得最终的检测结果。本发明通过考虑当前计算资源的负载情况，对音频数据进行缓冲处理，能够提高检测的精准度。本发明可广泛应用于婴儿声音分析技术领域。