Table 3:
Dataset | Input Feature | % Change in F1-Avg |
---|---|---|
DIAC-WOZ | Mel-spec | +4.36 |
Raw-audio | +2.16 | |
Wav2vec2.0 | +0.87 | |
CONVERGE | Mel-spec | +1.25 |
Raw-audio | +3.34 | |
XLSR-Mandarin | +0.33* |
indicates that the change is not statistically significant.
Dataset | Input Feature | % Change in F1-Avg |
---|---|---|
DIAC-WOZ | Mel-spec | +4.36 |
Raw-audio | +2.16 | |
Wav2vec2.0 | +0.87 | |
CONVERGE | Mel-spec | +1.25 |
Raw-audio | +3.34 | |
XLSR-Mandarin | +0.33* |
indicates that the change is not statistically significant.