@inproceedings{f434b4c930b34b8098612c79bf6a9369,
title = "TTS skins: Speaker conversion via ASR",
abstract = "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.",
keywords = "Human-computer interaction, Text to speech, Voice conversion",
author = "Adam Polyak and Lior Wolf and Yaniv Taigman",
note = "Publisher Copyright: Copyright {\textcopyright} 2020 ISCA; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",
year = "2020",
doi = "10.21437/Interspeech.2020-1416",
language = "الإنجليزيّة",
isbn = "9781713820697",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
pages = "786--790",
booktitle = "Interspeech 2020",
}