公开(公告)号：US20180182151A1

公开(公告)日：2018-06-28

申请号：US15389502

申请日：2016-12-23

Applicant: International Business Machines Corporation

Inventor： Wen LIU ,  Qin SHI ,  Shi Lei ZHANG ,  Peng Cheng ZHU

IPC: G06T13/20 ,  G10L15/26 ,  G10L15/02 ,  G10L13/10 ,  G06F17/28

CPC classification number: G06T13/205 ,  G06F17/2836 ,  G10L13/04 ,  G10L13/08 ,  G10L13/10

Abstract: According to an embodiment of the present invention, a computer-implemented method for modeling text-to-articulatory movement conversion is provided. In the method, text features are generated for a plurality of texts, wherein the text feature comprises a phoneme. Articulatory features are determined for the plurality of texts from a plurality of audio signals and a plurality of visual signals, wherein the audio signals record speeches of the plurality of texts, the visual signals record three-dimensional images of an articulator when speaking the plurality of texts, and the articulatory features indicate articulatory positions of the articulator in the speeches. A text-to-articulatory movement model is established with the text features as inputs and the articulatory features as outputs.