Voice input ending judgment method, device, equipment and system and storage medium

Abstract

The invention provides a voice input ending judgment method and device, equipment and a storage medium; the method comprises steps of detecting voice input of a user in real time, and analyzing text features and / or acoustic features of at least part of previously detected voice input to determine whether the user ends the voice input or not under the condition that it is detected that the time duration of no voice input exceeds a preset time threshold value. Therefore, the method can be regarded as a grading judgment scheme, for example, the method can be regarded as a grading judgment schemecombining voice activity detection and voice analysis. And as a primary judgment mode, voice activity detection does not need to have relatively high accuracy. Therefore, the time threshold value usedin voice activity detection can be set to be a small value; text feature analysis and / or acoustic feature analysis can be used as a judgment reassuring scheme, so that the accuracy of a judgment result can be ensured. Therefore, while the accuracy is ensured, the interaction delay can be greatly reduced, and the interaction experience of the user is improved.

Description

technical field [0001] The present disclosure relates to the technical field of voice interaction, and in particular to a method, device, device, system and storage medium for judging whether a user finishes voice input. Background technique [0002] Voice interaction belongs to the category of human-computer interaction, and it is a relatively cutting-edge interaction method that has been developed to the present. Voice interaction is the process in which users give instructions to the machine through natural language to achieve their own goals. During the voice interaction process, it is necessary to judge whether the user's voice input is finished, so as to obtain the complete voice input in time and improve the user's interaction experience. [0003] Currently, voice activity detection is mainly used to determine whether the user ends the voice input. Simply put, it is determined that the voice input ends when it is detected that the user does not have voice input for ...

AI Technical Summary

Problems solved by technology

This solution is relatively simple to implement, but a higher time threshold needs to be set to ensure the accuracy of the judgment result and reduce the false interruption rate

The higher the time threshold is set, the longer the user's waiting time will be, which will undoubtedly increase the interaction delay and reduce the user's interactive experience

Images