Method, system and device for converting voice into lip shape and storage medium
A voice conversion and voice technology, applied in voice analysis, character and pattern recognition, image data processing, etc., can solve problems such as time-consuming, loss of facial features, low resolution, etc., to reduce voice distortion and improve voice quality , smooth visual effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0041] In this embodiment, the process of converting speech into lip shapes is mainly performed using a trained generation confrontational network model (GAN), including:
[0042] get voice sequence;
[0043] Using the trained generation confrontation network model to receive the speech sequence and process it;
[0044] Obtain the lip image output by the trained GAN model.
[0045] Wherein, the generation confrontation network model includes a generation network G and a discrimination network D, the generation network G comprises a plurality of sub-networks, and the generation network is used to generate corresponding lip key points according to the received speech, while the discrimination network uses The key point of the lip shape is converted into a corresponding lip shape motion sequence, and the authenticity of the lip shape motion sequence is judged to finally output a lip shape image corresponding to the speech. refer to figure 1 , input a speech sequence into the t...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com