A three-dimensional modeling method for vocal organs

Abstract

The invention discloses a vocal organ three-dimensional modeling method which comprises the steps that an outer apparent vocal organ contour is extracted from a visible image, the contour is matched with a vocal organ universal three-dimensional geometrical model, and a reestablished outer apparent vocal organ three-dimensional model is obtained; an oral cavity inner vocal organ contour is extracted from an X-ray image, the contour is matched with the vocal organ universal three-dimensional geometrical model, and a reestablished oral cavity inner vocal organ three-dimensional model is obtained; and through the matching relation of the visible image and the X-ray image, the reestablished outer apparent vocal organ three-dimensional model and the reestablished oral cavity inner vocal organ three-dimensional model are fused, and accordingly an complete vocal organ three-dimensional model is obtained. According to the method, the vocal organ model which can reflect the real shape of a vocal organ from inside to outside during pronunciation by the vocal organ can be obtained accurately and quickly.

Description

technical field [0001] The invention relates to the technical fields of speech visualization, intelligent human-computer interaction, etc., and in particular to a three-dimensional modeling method of vocal organs. Background technique [0002] Viseme is the shape information of all pronunciation organs from the inside to the outside corresponding to the phoneme. With the advancement of magnetic resonance imaging technology that is harmless to the human body, it is possible to collect the three-dimensional shape data of the vocal organs, especially the vocal organs inside the oral cavity. [0003] However, because the acquisition equipment is too expensive and the acquisition process is expensive and the acquisition process is difficult to achieve real-time, it is still extremely difficult to quickly and accurately obtain the 3D model of the vocal organs of a specific person. In addition, the visible light image of a specific person can be obtained more conveniently and chea...

AI Technical Summary

Problems solved by technology

[0003] However, because the acquisition equipment is too expensive and the acquisition process is expensive, and the acquisition process is difficult to achieve real-time, it is still extremely difficult to quickly and accurately obtain the 3D model of the vocal organs of a specific person

In addition, the visible light image of a specific person can be obtained more conveniently and cheaply, but it can only obtain the external appearance information of the vocal organs

[0004] All in all, in the prior art, it is impossible to accurately obtain a vocal organ model that can reflect the true shape of the vocal organs during pronunciation from the inside to the outside

Images