Language Recognition Using Latent Dynamic Conditional Random Field Model with Phonological Features

<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 align="left">Feature</td><td align="center">Error (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td align="left">PF</td><td align="center"><b>17.46</b></td></tr><tr><td align="left">SDPF</td><td align="center">21.07</td></tr><tr><td align="left">MFCC</td><td align="center">25.48</td></tr><tr><td align="left">PLP</td><td align="center">19.51</td></tr><tr><td align="left">SDCPLP</td><td align="center">23.36</td></tr><tr><td align="left">SDC + PLP</td><td align="center">21.15</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr><tr class="table-fn"><td>The least error result is displayed in bold.<br/></td></tr></table>

Error of language classifiers using different speech feature sets (averaged across 28 pairs).

Mathematical Problems in Engineering

tab7

Table 7

Table 7: Language Recognition Using Latent Dynamic Conditional Random Field Model with Phonological Features 