Speaker Recognition Using Wavelet Cepstral Coefficient, I-Vector, and Cosine Distance Scoring and Its Application for Forensics

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Short-term feature extractor</td><td class="align_center">Accuracy rate of investigation (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">MFCCGMM</td><td class="align_center">82.46</td></tr><tr><td class="align_left">FMFCCPNN</td><td class="align_center">86.81</td></tr><tr><td class="align_left">MFCCICDS</td><td class="align_center">93.75</td></tr><tr><td class="align_left">WCCICDS</td><td class="align_center">95.48</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Journal of Electrical and Computer Engineering

tab3

Table 3

Table 3: Speaker Recognition Using Wavelet Cepstral Coefficient, I-Vector, and Cosine Distance Scoring and Its Application for Forensics 