End-to-End Speech Synthesis for Tibetan Multidialect

<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">Tibetan dialect</td><td class="align_center">MOS</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Lhasa-Ü-Tsang dialect</td><td class="align_center">3.95</td></tr><tr><td class="align_left">Amdo pastoral dialect</td><td class="align_center">4.18</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The MOS comparison of speech synthesized by different synthesis primitive models.</div>

Complexity

tab3

Table 3

Table 3: End-to-End Speech Synthesis for Tibetan Multidialect 