Feature Aggregation with Two-Layer Ensemble Framework for Multilingual Speech Emotion Recognition

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="6"><hr/></td></tr><tr class="thead"><td class="align_left">Training database</td><td class="align_center">Emotion</td><td class="align_center">F1 (Hz)</td><td class="align_center">F2 (Hz)</td><td class="align_center">F3 (Hz)</td><td class="align_center">F4 (Hz)</td></tr><tr><td class="thead-hr" colspan="6"><hr/></td></tr><tr><td class="align_left">IEMOCAP</td><td class="align_center"><i>Anger</i></td><td class="align_center">640</td><td class="align_center">1,768</td><td class="align_center">2,783</td><td class="align_center">3,808</td></tr><tr><td class="align_left">KETI</td><td class="align_center"><i>Anger</i></td><td class="align_center">370</td><td class="align_center">1,864</td><td class="align_center">2,832</td><td class="align_center">4,311</td></tr><tr class="table-tr"><td colspan="6"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>F1–F4 frequency differences in anger emotion between Korean and English.</div>

Mathematical Problems in Engineering

tab5

Table 5

Table 5: Feature Aggregation with Two-Layer Ensemble Framework for Multilingual Speech Emotion Recognition 