Auditory scene recognition method for artificial cochlea

The invention discloses an auditory scene recognition method for an artificial cochlea. The method comprises the steps that: (A) a pre-processing program module performs framing and windowing on a sound signal, (B) a feature extraction program module performs feature extraction on the preprocessed sound signal, and (C) a scene recognition program module performs a CNN operation on the sound signalwhich is subjected to feature extraction to obtain the probability value of each preset scene, determines a scene with a largest probability value as a final scene and outputs the scene. Through theCNN processing, different auditory scenes can be identified, instructions are provided for signal processing modules of subsequent speech enhancement, speech strategy and the like of a speech processor, therefore, the signal process of the speech processor is more matched with an auditory scene, a stimulation signal which is more matched with an actual auditory scene is outputted, the clarity andintelligibility of a speech