Table 1 Total number of audio samples in each dataset.
From: Speech emotion recognition with light weight deep neural ensemble model using hand crafted features
Dataset | Happy | Sad | Angry | Fear | Disgust | Surprise | Neutral | Total |
|---|---|---|---|---|---|---|---|---|
RAVDESS | 192 | 192 | 192 | 192 | 192 | 192 | 288 | 1440 |
TESS | 400 | 400 | 400 | 400 | 400 | 400 | 400 | 2800 |
SAVEE | 60 | 60 | 60 | 60 | 60 | 60 | 120 | 480 |
CREMA-D | 1271 | 1271 | 1271 | 1271 | 1271 | N/A | 1087 | 7442 |
EmoDB | 71 | 143 | 127 | 69 | 46 | N/A | 79 | 535 |
