TTS Skins: Speaker Conversion via ASR

Adam Polyak, Lior Wolf, Yaniv Taigman

We present a fully convolutional wav-to-wav network for converting between speakers’ voices, without relying on text. Our network is based on an encoder-decoder architecture, where the encoder is pre-trained for the task of Automatic Speech Recognition, and a multi-speaker waveform decoder is trained to reconstruct the original signal in an autoregressive manner. We train the network on narrated audiobooks, and demonstrate multi-voice TTS in those voices, by converting the voice of a TTS robot.

 DOI: 10.21437/Interspeech.2020-1416

Cite as: Polyak, A., Wolf, L., Taigman, Y. (2020) TTS Skins: Speaker Conversion via ASR. Proc. Interspeech 2020, 786-790, DOI: 10.21437/Interspeech.2020-1416.

  author={Adam Polyak and Lior Wolf and Yaniv Taigman},
  title={{TTS Skins: Speaker Conversion via ASR}},
  booktitle={Proc. Interspeech 2020},