Tuesday, November 19, 2019

Voice Cloning takes a very small sample of your voice and creates a synthetic model of your voice.

Voice Cloning takes a very small sample of your voice and creates a synthetic model of your voice.

Two Minute Papers explains a new technique that only needs 5 seconds of your real voice (it infers the rest).



Original “Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis” paper: https://arxiv.org/abs/1806.04558


No comments:

Post a Comment