%0 Conference Proceedings
%T fairseq S\²: A Scalable and Integrable Speech Synthesis Toolkit
%A Wang, Changhan
%A Hsu, Wei-Ning
%A Adi, Yossi
%A Polyak, Adam
%A Lee, Ann
%A Chen, Peng-Jen
%A Gu, Jiatao
%A Pino, Juan
%Y Adel, Heike
%Y Shi, Shuming
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F wang-etal-2021-fairseq
%X This paper presents fairseq S\², 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 S\² 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.
%R 10.18653/v1/2021.emnlp-demo.17
%U https://aclanthology.org/2021.emnlp-demo.17
%U https://doi.org/10.18653/v1/2021.emnlp-demo.17
%P 143-152