Skip to content

Latest commit

 

History

History
6 lines (5 loc) · 292 Bytes

README.md

File metadata and controls

6 lines (5 loc) · 292 Bytes

area_attention_for_SER

Speech emotion recogntion with area attention and VTLP

  1. Use process_dataset.py to divide IEMOCAP data set to train set and test set, and generate CSV files.
  2. Use vtlpAug.py to generate data augmented with VTLP.
  3. Use area_train.py to train and save the models.