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.


@inproceedings{Polyak2020,
  author={Adam Polyak and Lior Wolf and Yaniv Taigman},
  title={{TTS Skins: Speaker Conversion via ASR}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={786--790},
  doi={10.21437/Interspeech.2020-1416},
  url={http://dx.doi.org/10.21437/Interspeech.2020-1416}
}