The invention provides an audio
processing method and an intelligent
sound box. The method comprises the following steps: obtaining to-be-played audio data, and obtaining current operation informationwhich comprises an operation
voltage, an operation current and an operation
vibration amplitude; acquiring
magnetic field interference information of the current environment, and performing
noise reduction on the to-be-played audio according to the operation
voltage, the operation current and the
magnetic field interference information; performing voice endpoint detection on the to-be-played audio data, and performing
audio segmentation on the to-be-played audio data according to a voice endpoint detection result to obtain effective audio; and performing audio
noise reduction on the effectiveaudio in the to-be-played audio according to the operation
vibration amplitude, and playing the to-be-played audio data after audio
noise reduction. According to the invention, through obtaining themagnetic field interference information based on the current environment,
noise reduction is carried out on noise data generated in different
magnetic field interference environments, and the audio
noise reduction efficiency is improved.