Skip to main content

LipSense

Deep learning visual speech recognition model translating lip movements to text.

RoleResearch & ML Engineer
Timeline2024
Reading Time1 min read
PythonPyTorchOpenCVGRU NetworksCTC LossFastAPI

Context & Problem

Visual speech recognition (lip reading) is a challenging task in assistive technology and noisy environments. LipSense translates video sequences of lip movements to text using PyTorch, resolving spatial and temporal cues without audio feeds.

Architecture

System pipeline layout representing coordination blocks and execution pathways designed for this solution.

VIDEO FEEDLips ROI (30fps)3D-CNNFeature MatrixBI-GRUSequence DecodingTEXTCTC Output

Implementation

  • Designed a 3D Convolutional Neural Network (3D-CNN) to extract spatiotemporal visual features from lip movements.
  • Wired a Bidirectional GRU network to decode frame sequences into character probability matrices.
  • Tuned Connectionist Temporal Classification (CTC) Loss function parameters to train the model end-to-end without frame alignments.

Challenges & Trade-offs

CHALLENGE: Drastic variations in lighting and speaker head orientations.

RESOLUTION: Implemented a dynamic face-alignment step using MediaPipe landmarks, normalising coordinates and bounding box scales around the lips ROI prior to classification.

Results & Impact

Quantitative metrics and verified outcomes obtained from benchmarks.

95.2%Transcription Accuracy
4.8%Word Error Rate (WER)
30fpsExtraction Speed

© 2026 Faizal Shaikh. All rights reserved.

Meticulously engineered using Next.js, Tailwind CSS, and Framer Motion.

Based in Mumbai, India