The Technique of English Word Syllable Division in Speech Synthesis Based on Neural Network

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Word vector dimension</td><td class="align_center">Error rate (%)</td><td class="align_center">Time</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">5</td><td class="align_center">14.6</td><td class="align_center">About 5 hours</td></tr><tr><td class="align_left">10</td><td class="align_center">10.0</td><td class="align_center">About 7 hours</td></tr><tr><td class="align_left">20</td><td class="align_center">9.82</td><td class="align_center">About 9 hours</td></tr><tr><td class="align_left">60</td><td class="align_center">9.95</td><td class="align_center">About 12 hours</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Relation between input feature dimension and error rate.</div>

Mathematical Problems in Engineering

tab3

Table 3

Table 3: The Technique of English Word Syllable Division in Speech Synthesis Based on Neural Network 