Robustness simulated recording condition

83.3% passed tests (5 passed / 1 failed).

Percentage Unchanged Predictions Simulated Position

Threshold: 0.8

Data

Percentage Unchanged Predictions Simulated Position

emovo-1.2.1-emotion.test

0.88

imda-nsc-read-speech-balanced-2.6.0-headset

0.92

timit-1.4.1-files

0.89

mean

0.90

Percentage Unchanged Predictions Simulated Room

Threshold: 0.8

Data

Percentage Unchanged Predictions Simulated Room

emovo-1.2.1-emotion.test

0.83

imda-nsc-read-speech-balanced-2.6.0-headset

0.88

timit-1.4.1-files

0.79

mean

0.83

Visualization Simulated Position

Confusion Matrix showing the shift from the predictions of audio with a baseline simulated position to the predictions of audio with a different simulated position.

../../../_images/visualization-simulated-position_emovo-1.2.1-emotion.test25.png
../../../_images/visualization-simulated-position_imda-nsc-read-speech-balanced-2.6.0-headset25.png
../../../_images/visualization-simulated-position_timit-1.4.1-files25.png

Visualization Simulated Room

Confusion Matrix showing the shift from the predictions of audio with a baseline simulated room to the predictions of audio with a different simulated room.

../../../_images/visualization-simulated-room_emovo-1.2.1-emotion.test25.png
../../../_images/visualization-simulated-room_imda-nsc-read-speech-balanced-2.6.0-headset25.png
../../../_images/visualization-simulated-room_timit-1.4.1-files25.png