Chinese sentence level lip language recognition method combining DenseNet and resBi-LSTM
A recognition method and sentence-level technology, applied in speech recognition, character and pattern recognition, speech analysis, etc., can solve the problem of lack of large-scale sentence-level Chinese lip language recognition public datasets, etc., to encourage feature reuse, reduce difficulty, Enhance the effect of feature propagation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0038] The present invention will be further described below in conjunction with accompanying drawing:
[0039] The present invention uses a self-made Chinese sentence-level lip recognition data set (from news broadcast and Luo Ji thinking program) to conduct lip recognition research. The method flowchart that the present invention proposes can be seen figure 1 , divided into two models, namely the pinyin prediction model ( figure 2 ) and language translation model ( image 3 ). Among them, the pinyin translation model is divided into three steps: visual feature extraction, feature sequence processing, and time series data classification.
[0040] Step 1, visual feature extraction:
[0041] The input of the pinyin prediction model is a sequence of lip pictures. Assuming that the input sequence is T×H×W (time×height×width), first use spatiotemporal convolution to extract spatiotemporal features and capture the short-term motion features of the lip area. The use of 64 thre...
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