@inproceedings{ebddd80108b4487b9a35d70bfe151c6d,
title = "FAIRSEQ S2: A Scalable and Integrable Speech Synthesis Toolkit",
abstract = "This paper presents FAIRSEQ S2, a FAIRSEQ extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker variants. To enable training speech synthesis models with less curated data, a number of preprocessing tools are built and their importance is shown empirically. To facilitate faster iteration of development and analysis, a suite of automatic metrics is included. Apart from the features added specifically for this extension, FAIRSEQ S2 also benefits from the scalability offered by FAIRSEQ and can be easily integrated with other state-of-the-art systems provided in this framework. The code, documentation, and pre-trained models will be made available at https://github.com/pytorch/fairseq/tree/master/examples/speech_synthesis.",
author = "Changhan Wang and Hsu, {Wei Ning} and Yossi Adi and Adam Polyak and Ann Lee and Chen, {Peng Jen} and Jiatao Gu and Juan Pino",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2021 ; Conference date: 07-11-2021 Through 11-11-2021",
year = "2021",
doi = "10.18653/v1/2021.emnlp-demo.17",
language = "الإنجليزيّة",
series = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
publisher = "Association for Computational Linguistics (ACL)",
pages = "143--152",
booktitle = "EMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing",
address = "الولايات المتّحدة",
}