Intelligent track division method, device and system for monaural call recording

The invention discloses an intelligent track division method, device and system for monaural call recording, which are used for separating multi-person voices in monaural call recording, and the method comprises the following steps: preprocessing audio data of the call recording to obtain preprocessed audio data; performing frame attribute detection on the preprocessed audio data, and judging frame attribute information of each frame in the audio data; determining a voice starting point in the audio data according to the frame attribute information of each frame in the audio data, and deleting the audio data before the voice starting point to obtain pure voice audio data; and inputting the pure voice audio data into a track division model to obtain track division information of the pure voice audio data. According to the technical scheme, voice starting point detection is carried out firstly, interference is eliminated, only a pure voice part is reserved, and then actual speaker roles are separated out for su