SPEECH SYNTHESIS METHOD AND DEVICE

专利名称：SPEECH SYNTHESIS METHOD AND DEVICE发明人：Liqun Deng,Jiansheng Wei,Wenhua Sun申请号：US17225376申请日：20210408

公开号：US20210287657A1公开日：20210916

专利附图：

摘要：In a speech synthesis method, an emotion intensity feature vector is set for atarget synthesis text, an acoustic feature vector corresponding to an emotion intensity isgenerated based on the emotion intensity feature vector by using an acoustic model, anda speech corresponding to the emotion intensity is synthesized based on the acoustic

feature vector. The emotion intensity feature vector is continuously adjustable, andemotion speeches of different intensities can be generated based on values of differentemotion intensity feature vectors, so that emotion types of a synthesized speech aremore diversified. This application may be applied to a human-computer interactionprocess in the artificial intelligence (AI) field, to perform intelligent emotion speechsynthesis.

申请人：HUAWEI TECHNOLOGIES CO., LTD.

地址：Shenzhen CN

国籍：CN

更多信息请下载全文后查看