Acoustic Model with Multiple Lexicon Types for Indonesian Speech Recognition

<table class="table-group" id="tab16"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_center" colspan="3">WER (%)</td></tr><tr class="thead"><td class="align_left">Lexicon type</td><td class="align_center">TDNNF</td><td class="align_center">CNN-TDNNF-augmented</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">4-combination</td><td class="align_center">24.96</td><td class="align_center"><b>19.03</b></td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The performance of the models.</div>

Applied Computational Intelligence and Soft Computing

tab16

Table 16

Table 16: Acoustic Model with Multiple Lexicon Types for Indonesian Speech Recognition 