Practical Speech Emotion Recognition Based on Online Learning: From Acted Data to Elicited Data

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="265819.fig.0012a" src="https://static.hindawi.com/articles/mpe/volume-2013/265819/figures/265819.fig.0012a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>Normalised mean pitch frequency</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="265819.fig.0012b" src="https://static.hindawi.com/articles/mpe/volume-2013/265819/figures/265819.fig.0012b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>Mean first formant frequency (Hz)</td></tr></table></td></tr><tr class="fig-image" id="c"><td><img alt="265819.fig.0012c" src="https://static.hindawi.com/articles/mpe/volume-2013/265819/figures/265819.fig.0012c.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(c) </b>Mean second formant frequency (Hz)</td></tr></table></td></tr><tr class="fig-image" id="d"><td><img alt="265819.fig.0012d" src="https://static.hindawi.com/articles/mpe/volume-2013/265819/figures/265819.fig.0012d.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(d) </b>Mean third formant frequency (Hz)</td></tr></table></td></tr></table>

<table>Feature distribution over various emotional states.</table>

Mathematical Problems in Engineering

fig12

Figure 12

Figure 12: Practical Speech Emotion Recognition Based on Online Learning: From Acted Data to Elicited Data 