astorfi/lip-reading-deeplearning

Health v2 · maintenance only

Adoption not part of the score

1904 stars · 331 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow implementation of coupled 3D convolutional neural networks for cross audio-visual matching recognition, accompanying an IEEE Access paper. It supports lip reading as a primary application of the audio-visual recognition model.

Use cases

• lip reading from video
• audio-visual speech recognition
• train a 3D CNN for cross-modal matching
• visual speech recognition research
• reproduce results from the 3D CNN audio-visual paper

When to choose

• you need a research-grade implementation of 3D CNN lip reading in TensorFlow
• you want to reproduce or extend the coupled 3D CNN audio-visual matching paper
• you are studying cross-modal audio-visual recognition architectures

When to avoid

• you need a production-ready lip reading system with a prepared input pipeline
• you want a maintained library with recent updates and broad community support
• you need support for modern frameworks like PyTorch

Facets

library · maturity maintenance

deep-learning speech-recognition computer-vision machine-learning deep-learning computer-vision speech-processing artificial-intelligence python lip-reading 3d-convolutional-network audio-visual-recognition tensorflow research-code linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="astorfi/lip-reading-deeplearning")