Skip to content

Latest commit

 

History

History
11 lines (6 loc) · 478 Bytes

File metadata and controls

11 lines (6 loc) · 478 Bytes

Audio-Emotion-Analyzer-Through-Deep-Learning

Final year capstone project for SCOPE school of VIT, Vellore.

Key Methodology Adopted: A custom transformer model leveraging bi-directional LSTM with a modified encoder-decoder architecture employing scaled-dot product attention mechanism. Refer notebooks for more depth.

[Update]: Got accepted @ an IEEE conference - ICCCNT 2023 held at IIT Delhi

URL to the paper:

https://ieeexplore.ieee.org/document/10307561