In this study, we present recent developments on ESPnet: End-to-End Speech Processing toolkit, which mainly involves a recently proposed architecture called Conformer, Convolution-augmented Transformer. This paper shows the results for a wide range of end-to-end speech processing applications, such as automatic speech recognition (ASR), speech translations (ST), speech separation (SS) and text-to-speech (TTS). Our experiments reveal various training tips and significant performance benefits obtained with the Conformer on different tasks. These results are competitive or even outperform the current state-of-art Transformer models. We are preparing to release all-in-one recipes using open source and publicly available corpora for all the above tasks with pre-trained models. Our aim for this work is to contribute to our research community by reducing the burden of preparing state-of-the-art research environments usually requiring high resources.
@article{arxiv.2010.13956,
title = {Recent Developments on ESPnet Toolkit Boosted by Conformer},
author = {Pengcheng Guo and Florian Boyer and Xuankai Chang and Tomoki Hayashi and Yosuke Higuchi and Hirofumi Inaguma and Naoyuki Kamo and Chenda Li and Daniel Garcia-Romero and Jiatong Shi and Jing Shi and Shinji Watanabe and Kun Wei and Wangyou Zhang and Yuekai Zhang},
journal= {arXiv preprint arXiv:2010.13956},
year = {2020}
}