Speech recognition-based self-learning method and self-learning device of a toy

Abstract

The invention discloses a toy self-cleaning method and device based on voice recognition. The self-learning method comprises the steps that a voice acquisition prompt is output, and a voice acquisition device is started; the voice acquisition device acquires first voice data and extracts feature data of the first voice data; the voice acquisition device acquires second voice data matched with the first voice data; the first video data and the second video data are related and stored. The voice acquisition device acquires the first voice data and extracts the feature data of the video data after the prompt is output, the second video data and the first video data are related and stored after the second video data matched with the first video data is collected, toy self-cleaning for voice is achieved, the toy language limitation caused by prestored voice is avoided, and the phenomenon that different voice data is prestored for different language regions in the toy manufacturing process is avoided.

Description

technical field [0001] The invention relates to the field of intelligent toys, in particular to a speech recognition-based self-learning method and a self-learning device for toys. Background technique [0002] With the continuous development of electronic technology and artificial intelligence, toys, as a kind of electronic equipment for specific user groups, are favored by more and more people because of their good interactivity, such as saying "sing" to toys, and toys recognize After the "sing" command, the pre-stored song will be played. [0003] However, the existing toy can only be regarded as a toy that interacts according to a preset script, and the diversity of its interaction methods is limited by the number of scripts input during toy production. If the number of preset scripts is 3, then the toy It can only respond to 3 kinds of voice content; if the number of preset scripts is 10, then the toy can only respond to 10 kinds of voice content. Then when children e...

AI Technical Summary

Problems solved by technology

[0003] However, the existing toy can only be regarded as a toy that interacts according to a preset script, and the diversity of its interaction methods is limited by the number of scripts input during toy production. If the number of preset scripts is 3, then the toy It can only respond to 3 kinds of voice content; if the number of preset scripts is 10, then the toy can only respond to 10 kinds of voice content

Then when children experience the toy for a period of time, because the interactive content is not updated, the interactivity of children's toys will gradually decrease and the toy function will be lost.

Images