Update README.md
Browse files
README.md
CHANGED
|
@@ -35,7 +35,7 @@ This is the model that got first place in the SER track of the Automatic Speech
|
|
| 35 |
|
| 36 |
The following datasets were used in the training:
|
| 37 |
|
| 38 |
-
- [CORAA SER v1.0](https://github.com/rmarcacini/ser-coraa-pt-br/): a dataset composed of spontaneous portuguese speech and approximately
|
| 39 |
|
| 40 |
- [EMOVO Corpus](https://aclanthology.org/L14-1478/): a database of emotional speech for the Italian language, built from the voices of up to 6 actors who played 14 sentences simulating 6 emotional states (disgust, fear, anger, joy, surprise, sadness) plus the neutral state.
|
| 41 |
|
| 35 |
|
| 36 |
The following datasets were used in the training:
|
| 37 |
|
| 38 |
+
- [CORAA SER v1.0](https://github.com/rmarcacini/ser-coraa-pt-br/): a dataset composed of spontaneous portuguese speech and approximately 40 minutes of audio segments labeled in three classes: neutral, non-neutral female, and non-neutral male.
|
| 39 |
|
| 40 |
- [EMOVO Corpus](https://aclanthology.org/L14-1478/): a database of emotional speech for the Italian language, built from the voices of up to 6 actors who played 14 sentences simulating 6 emotional states (disgust, fear, anger, joy, surprise, sadness) plus the neutral state.
|
| 41 |
|