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.
@article{arxiv.1904.08983,
title = {TTS Skins: Speaker Conversion via ASR},
author = {Adam Polyak and Lior Wolf and Yaniv Taigman},
journal= {arXiv preprint arXiv:1904.08983},
year = {2020}
}