s0nicboOm / ravdess_ser

Simple speech emotion recognition (FC, GRU, LSTM) using RAVDESS dataset

RAVDES SER

Speeh emotion recognition using RAVDESS dataset
contact: [e-mail]

Feature used

Read the the following blog (in Indonesian language): https://bagustris.blogspot.com/2019/06/implementasi-pengenalan-emosi-dari.html

Classifier

Dense (Fully Connected) Vs GRU Vs LSTM

Current results

script_name = accuracy x 100%
ser_ravdess = 0.67
ser_ravdess-gru = 0.68
ser_ravdess-lstm = 0.70

Citation

If you get a benefit from this repo, please cite the following paper:

B.T. Atmaja and M. Akagi, “On The Differences Between Song and Speech Emotion
Recognition: Effect of Feature Sets, Feature Types, and Classifiers”, TENCON 2020
- 2020 IEEE Region 10 Conference (TENCON), Osaka, Japan, 2020.

See the my other repo, https://github.com/bagustris/ravdess_song_speech, for comparison of speech and song emotion recognition.