A Multiscale Chaotic Feature Extraction Method for Speaker Recognition

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left">Feature</td><td class="align_center">Acoustic feature</td><td class="align_center">Nonlinear feature</td><td class="align_center">Chaotic feature</td><td class="align_center"><i>i</i>-vector model</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">EER (%)</td><td class="align_center">2.562</td><td class="align_center">2.833</td><td class="align_center">2.149</td><td class="align_center">2.497</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The EER value under clean speech condition.</div>

Complexity

tab3

Table 3

Table 3: A Multiscale Chaotic Feature Extraction Method for Speaker Recognition 