Convolutional neural network to predict language-independent emotion on a dataset of English and French speech.
This model is trained on a merged dataset of natural speech with data provided by IEMOCAP for english speech samples and Recola for french speech samples.
The implementation is a basis for a research paper on comparison on different optimization algorithms and activation functions.
You can view the notebook here.
- Python 3
- Tensorflow
Simply open a new terminal in the directory and type:
> jupyter notebook
- F. Strohm - StrohmFn
- C. Tasci - StraysWonderland
Class | Mono-lingual | Multi-lingual | Cross-language |
---|---|---|---|
Sadness | 0.000 | 0.015 | 0.015 |
Anger | 0.019 | 0.014 | 0.014 |
Pleasure | 0.043 | 0.010 | 0.120 |
Joy | 0.942 | 0.985 | 0.864 |
MICRO | 0.421 | 0.432 | 0.405 |
Class | Mono-lingual | Multi-lingual | Cross-language |
---|---|---|---|
Sadness | 0.070 | 0.000 | 0.230 |
Anger | 0.200 | 0.200 | 0.200 |
Pleasure | 0.350 | 0.035 | 0.357 |
Joy | 0.754 | 0.912 | 0.403 |
MICRO | 0.533 | 0.524 | 0.359 |