@inproceedings{d4ae827fbdab4fdfa94e3a3dbbd6f910,
title = "Unsupervised Polyglot Text-to-speech",
abstract = "We present a TTS neural network that is able to produce speech in multiple languages. The proposed network is able to transfer a voice, which was presented as a sample in a source language, into one of several target languages. Training is done without using matching or parallel data, i.e., without samples of the same speaker in multiple languages, making the method much more applicable. The conversion is based on learning a polyglot network that has multiple per-language sub-networks and adding loss terms that preserve the speaker's identity in multiple languages. We evaluate the proposed polyglot neural network for three languages with a total of more than 400 speakers and demonstrate convincing conversion capabilities.",
keywords = "TTS, multilingual, unsupervised learning",
author = "Eliya Nachmani and Lior Wolf",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; null ; Conference date: 12-05-2019 Through 17-05-2019",
year = "2019",
month = may,
doi = "10.1109/ICASSP.2019.8683519",
language = "אנגלית",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7055--7059",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "ארצות הברית",
}