Information processing method and device and storage medium

Abstract

The invention relates to an information processing method and device and a storage medium. The method comprises the steps of obtaining a current audio, and obtaining a current text corresponding to the current audio; performing feature extraction on the current audio based on a voice feature extraction part contained in the semantic analysis model to obtain a voice feature of the current audio; performing feature extraction on the current text based on a text feature extraction part contained in the semantic analysis model to obtain text features of the current text; performing semantic classification processing on the voice features and the text features by utilizing a classification part contained in the semantic analysis model to obtain a classification result; and refusing to identifythe current audio when the classification result shows that the current audio is the audio refusing to be identified. Thus, the meaning to be expressed by the current audio can be determined more accurately, so that the extracted features are higher in accuracy, and then an accurate classification result is determined; and the probability of false response can be reduced, and unnecessary semanticanalysis processes can also be reduced.

Description

technical field [0001] The present disclosure relates to the field of computer communication, and in particular to an information processing method, device and storage medium. Background technique [0002] In the process of man-machine dialogue, full-duplex mainly refers to the technical means used to achieve a smooth, natural and anthropomorphic dialogue experience. At present, full-duplex technology can be applied to various application scenarios in audio interaction such as "one wake-up, continuous dialogue", "listening and talking, interrupting at any time", so as to make the audio interaction process smoother. [0003] At present, the audio interaction technology has been applied to various electronic devices, for example, mobile terminals, televisions, smart speakers, and the like. In the process of audio interaction based on electronic devices, the electronic device receives a large amount of audio requests, but not all received audio requests are the requests that t...

AI Technical Summary

Problems solved by technology

In the process of audio interaction based on electronic devices, the electronic device receives a large amount of audio requests, but not all received audio requests are the requests that the user really wants to express. At this time, there may be false wakeups, Misresponses, such as responding to irrelevant audio requests and unintentional self-talk from the user

Images