|
--- |
|
title: README |
|
emoji: 🐠 |
|
colorFrom: indigo |
|
colorTo: purple |
|
sdk: static |
|
pinned: false |
|
--- |
|
|
|
# ESPnet: end-to-end speech processing toolkit |
|
|
|
ESPnet is an end-to-end speech processing toolkit covering end-to-end speech recognition, text-to-speech, speech translation, speech enhancement, speaker diarization, spoken language understanding, and so on. |
|
ESPnet uses [pytorch](http://pytorch.org/) as a deep learning engine and also follows [Kaldi](http://kaldi-asr.org/) style data processing, feature extraction/format, and recipes to provide a complete setup for various speech processing experiments. |
|
|
|
|
|
<details><summary>Citing ESPnet</summary> |
|
|
|
```BibTex |
|
@inproceedings{watanabe2018espnet, |
|
author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson {Enrique Yalta Soplin} and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, |
|
title={{ESPnet}: End-to-End Speech Processing Toolkit}, |
|
year={2018}, |
|
booktitle={Proceedings of Interspeech}, |
|
pages={2207--2211}, |
|
doi={10.21437/Interspeech.2018-1456}, |
|
url={http://dx.doi.org/10.21437/Interspeech.2018-1456} |
|
} |
|
|
|
@inproceedings{hayashi2020espnet, |
|
title={{Espnet-TTS}: Unified, reproducible, and integratable open source end-to-end text-to-speech toolkit}, |
|
author={Hayashi, Tomoki and Yamamoto, Ryuichi and Inoue, Katsuki and Yoshimura, Takenori and Watanabe, Shinji and Toda, Tomoki and Takeda, Kazuya and Zhang, Yu and Tan, Xu}, |
|
booktitle={Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, |
|
pages={7654--7658}, |
|
year={2020}, |
|
organization={IEEE} |
|
} |
|
|
|
@inproceedings{inaguma-etal-2020-espnet, |
|
title = "{ESP}net-{ST}: All-in-One Speech Translation Toolkit", |
|
author = "Inaguma, Hirofumi and |
|
Kiyono, Shun and |
|
Duh, Kevin and |
|
Karita, Shigeki and |
|
Yalta, Nelson and |
|
Hayashi, Tomoki and |
|
Watanabe, Shinji", |
|
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations", |
|
month = jul, |
|
year = "2020", |
|
address = "Online", |
|
publisher = "Association for Computational Linguistics", |
|
url = "https://www.aclweb.org/anthology/2020.acl-demos.34", |
|
pages = "302--311", |
|
} |
|
|
|
@inproceedings{li2020espnet, |
|
title={{ESPnet-SE}: End-to-End Speech Enhancement and Separation Toolkit Designed for {ASR} Integration}, |
|
author={Chenda Li and Jing Shi and Wangyou Zhang and Aswin Shanmugam Subramanian and Xuankai Chang and Naoyuki Kamo and Moto Hira and Tomoki Hayashi and Christoph Boeddeker and Zhuo Chen and Shinji Watanabe}, |
|
booktitle={Proceedings of IEEE Spoken Language Technology Workshop (SLT)}, |
|
pages={785--792}, |
|
year={2021}, |
|
organization={IEEE}, |
|
} |
|
|
|
@article{arora2021espnet, |
|
title={ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet}, |
|
author={Arora, Siddhant and Dalmia, Siddharth and Denisov, Pavel and Chang, Xuankai and Ueda, Yushi and Peng, Yifan and Zhang, Yuekai and Kumar, Sujay and Ganesan, Karthik and Yan, Brian and others}, |
|
journal={arXiv preprint arXiv:2111.14706}, |
|
year={2021} |
|
} |
|
|
|
</details> |
|
|
