DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning

<table class="table-group" id="tab7"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Acoustic model</td><td class="align_center">WER (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">DCNN-CTC</td><td class="align_center">20.18</td></tr><tr><td class="align_left">SE-MCNN-CTC</td><td class="align_center">23.05</td></tr><tr><td class="align_left">DCNN-BGRU-CTC</td><td class="align_center">18.13</td></tr><tr><td class="align_left">DLD</td><td class="align_center">14.28</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>WER of different acoustic model on THCHS-30.</div>

Complexity

tab7

Table 7

Table 7: DLD: An Optimized Chinese Speech Recognition Model Based on Deep Learning 