General Conference of the Institute of Electronics, Information and Communication Engineers
Advanced Search

Presentation Information

9:00 AM - 10:30 AM JST(12:00 AM - 1:30 AM UTC)

[TPO-1-03]Evaluating Zero-Shot TTS Models Based on Consistency of Speaker Embedding Clusters

〇Natsuki Asano1, Sviridova Nina2 (1. TokyoCity University, 2. International Research Center for Neurointelligence, The University of Tokyo)

Keywords:

Zero-Shot TTS,synthesized voice

Back to Session information