Hello everyone, this post is a brief summary of my first meeting with my mentor Jungseock.
Project: We will redirect the project. Something on Audio-Visual speech recognition.
- Integrating contexts in Audio-Visual speech recognition
- Emotion recognition in Audio-Visual
- Movie data: scripts can be labels/hints for different emotions
Long-term Goal: turn the work into publications
Current work to do:
- Get familiar with speech: signal processing, run RNN, LSTM, Attention
- Search for papers about emotion
- Search for papers about movie data
- Run OpenPose
To be continued…