Table 2 Available data streams.
From: Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals
Modality | Details | Count | Device | File format |
|---|---|---|---|---|
Audio | Main stream, 48000 Hz, 2 channels, 24 bit, Pulse Code Modulation (PCM) | 2 | Zoom H4n | WAV |
Audio | Auxiliary stream 48000 Hz, 2 channels, 16 bit, AAC | 4 | Panasonic HC-VX9805 | WAV |
Video | (face, left posture, right posture, back), 1080p, 50 fps, h264 | 4 | Panasonic HC-VX9805 | MP4 |
EDA | Auxiliary skin conductance, 4 Hz | 1 | Empatica E4 | CSV |
Temperature | Auxiliary skin temperature, 4 Hz | 1 | Empatica E4 | CSV |
Acceleration | Acceleration (x,y,z), 32 Hz | 3 | Empatica E4 | CSV |
Heart activity | RR (Interbeat) intervals | 1 | Empatica E4 | CSV |
Acceleration | Acceleration (x,y,z), 250 Hz | 3 | Faros 180 | CSV |
Heart activity | ECG, 1000 Hz, 24 bit | 1 | Faros 180 | CSV |
