A processing method of text and speech information is used to improve the asynchrony between text content and speech content in the prior art, including: identifying text information in the target picture; extracting the first key information of the text information, which includes the set of text keywords and each text keyword. The corresponding word frequency; acquiring the speech file corresponding to the text information; mapping the speech file to the first preset coordinate position in the target picture if the word frequency corresponding to the text keyword is larger than the threshold value. The method improves the situation that the text content is not synchronized with the voice content in the existing technology.
【技术实现步骤摘要】
【国外来华专利技术】PCT国内申请,说明书已公开。
【技术保护点】
PCT国内申请,权利要求书已公开。
【技术特征摘要】
【国外来华专利技术】2017.02....
【专利技术属性】
技术研发人员:李小娟,郜文美,
申请(专利权)人:华为技术有限公司,
类型:发明
国别省市:广东,44
还没有人留言评论。发表了对其他浏览者有用的留言会获得科技券。