Robustness background noise

33.3% passed tests (8 passed / 16 failed).

Change Ccc Babble Noise

Threshold: -0.05

Data

Change CCC Babble Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.02

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.01

mean

-0.01

Change Ccc Coughing

Threshold: -0.05

Data

Change CCC Coughing

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.08

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

-0.12

mean

-0.10

Change Ccc Environmental Noise

Threshold: -0.05

Data

Change CCC Environmental Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.02

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.01

mean

-0.01

Change Ccc Music

Threshold: -0.05

Data

Change CCC Music

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.03

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.01

mean

-0.01

Change Ccc Sneezing

Threshold: -0.05

Data

Change CCC Sneezing

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.05

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

-0.10

mean

-0.08

Change Ccc White Noise

Threshold: -0.05

Data

Change CCC White Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

-0.04

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.02

mean

-0.01

Percentage Unchanged Predictions Babble Noise

Threshold: 0.9

Data

Percentage Unchanged Predictions Babble Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.81

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.71

mean

0.76

Percentage Unchanged Predictions Coughing

Threshold: 0.9

Data

Percentage Unchanged Predictions Coughing

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.55

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.37

mean

0.46

Percentage Unchanged Predictions Environmental Noise

Threshold: 0.9

Data

Percentage Unchanged Predictions Environmental Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.79

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.80

mean

0.80

Percentage Unchanged Predictions Music

Threshold: 0.9

Data

Percentage Unchanged Predictions Music

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.80

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.77

mean

0.79

Percentage Unchanged Predictions Sneezing

Threshold: 0.9

Data

Percentage Unchanged Predictions Sneezing

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.58

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.32

mean

0.45

Percentage Unchanged Predictions White Noise

Threshold: 0.9

Data

Percentage Unchanged Predictions White Noise

iemocap-2.3.0-emotion.dimensions.test.gold_standard

0.48

msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard

0.73

mean

0.60

Visualization Babble Noise

Difference of predictions for clean audio and audio with added babble noise. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-babble-noise_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-babble-noise_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png

Visualization Coughing

Difference of predictions for clean audio and audio with added coughing. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-coughing_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-coughing_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png

Visualization Environmental Noise

Difference of predictions for clean audio and audio with added environmental noise. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-environmental-noise_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-environmental-noise_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png

Visualization Music

Difference of predictions for clean audio and audio with added music. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-music_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-music_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png

Visualization Sneezing

Difference of predictions for clean audio and audio with added sneezing. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-sneezing_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-sneezing_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png

Visualization White Noise

Difference of predictions for clean audio and audio with added white noise. The allowed prediction difference \(\delta < 0.05\) is highlighted in green in the upper plot. The lower plot shows the distributions of the two predictions.

../../../_images/visualization-white-noise_iemocap-2.3.0-emotion.dimensions.test.gold_standard31.png
../../../_images/visualization-white-noise_msppodcast-2.6.1-emotion.dimensions.test-1.gold_standard31.png