@inproceedings{333619a34def4df185cc0b3e3701e90e,
title = "Fitting new speakers based on a short untranscribed sample",
abstract = "Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is cur-rently largely unrealized. We present a method that is designed to capture a new speaker from a short untranscribed audio sample. This is done by employing an additional network that given an audio sample, places the speaker in the embedding space. This network is trained as part of the speech synthesis system using various consistency losses. Our results demonstrate a greatly im-proved performance on both the dataset speakers, and, more importantly, when fitting new voices, even from very short samples.",
author = "Eliya Nachmani and Adam Polyak and Yaniv Taigman and Lior Wolf",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2018.; 35th International Conference on Machine Learning, ICML 2018 ; Conference date: 10-07-2018 Through 15-07-2018",
year = "2018",
language = "الإنجليزيّة",
series = "35th International Conference on Machine Learning, ICML 2018",
pages = "5932--5940",
editor = "Jennifer Dy and Andreas Krause",
booktitle = "35th International Conference on Machine Learning, ICML 2018",
}