From 251c6690ae3de6d04454876fbb864e8664951bc8 Mon Sep 17 00:00:00 2001 From: Harry He <68176557+HarryHe11@users.noreply.github.com> Date: Fri, 6 Sep 2024 21:52:56 +0800 Subject: [PATCH] update Amphion/Emilia references (#271) * Update Amphion/Emilia * Update README.md * Update README.md * Update README.md --- README.md | 12 ++++++------ preprocessors/Emilia/README.md | 23 +++++++++++------------ 2 files changed, 17 insertions(+), 18 deletions(-) diff --git a/README.md b/README.md index 6167bad2..59c566d0 100644 --- a/README.md +++ b/README.md @@ -29,6 +29,7 @@ In addition to the specific generation tasks, Amphion includes several **vocoders** and **evaluation metrics**. A vocoder is an important module for producing high-quality audio signals, while evaluation metrics are critical for ensuring consistent metrics in generation tasks. Moreover, Amphion is dedicated to advancing audio generation in real-world applications, such as building **large-scale datasets** for speech synthesis. ## πŸš€Β News +- **2024/09/01**: [Amphion](https://arxiv.org/abs/2312.09911) and [Emilia](https://arxiv.org/abs/2407.05361) got accepted by IEEE SLT 2024! πŸ€— - **2024/08/28**: Welcome to join Amphion's [Discord channel](https://discord.com/invite/ZxxREr3Y) to stay connected and engage with our community! - **2024/08/27**: *The Emilia dataset is now publicly available!* Discover the most extensive and diverse speech generation dataset with 101k hours of in-the-wild speech data now at [![hf](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/amphion/Emilia-Dataset) or [![OpenDataLab](https://img.shields.io/badge/OpenDataLab-Dataset-blue)](https://opendatalab.com/Amphion/Emilia)! πŸ‘‘πŸ‘‘πŸ‘‘ - **2024/07/01**: Amphion now releases **Emilia**, the first open-source multilingual in-the-wild dataset for speech generation with over 101k hours of speech data, and the **Emilia-Pipe**, the first open-source preprocessing pipeline designed to transform in-the-wild speech data into high-quality training data with annotations for speech generation! [![arXiv](https://img.shields.io/badge/arXiv-Paper-COLOR.svg)](https://arxiv.org/abs/2407.05361) [![hf](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/amphion/Emilia) [![demo](https://img.shields.io/badge/WebPage-Demo-red)](https://emilia-dataset.github.io/Emilia-Demo-Page/) [![readme](https://img.shields.io/badge/README-Key%20Features-blue)](preprocessors/Emilia/README.md) @@ -156,11 +157,10 @@ Amphion is under the [MIT License](LICENSE). It is free for both research and co ## πŸ“š Citations ```bibtex -@article{zhang2023amphion, - title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit}, - author={Xueyao Zhang and Liumeng Xue and Yicheng Gu and Yuancheng Wang and Haorui He and Chaoren Wang and Xi Chen and Zihao Fang and Haopeng Chen and Junan Zhang and Tze Ying Tang and Lexiao Zou and Mingxuan Wang and Jun Han and Kai Chen and Haizhou Li and Zhizheng Wu}, - journal={arXiv}, - year={2024}, - volume={abs/2312.09911} +@inproceedings{amphion, +author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and Li, Jiaqi and He, Haorui and Wang, Chaoren and Song, Ting and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng}, +title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit}, +booktitle={Proc.~of SLT}, +year={2024} } ``` diff --git a/preprocessors/Emilia/README.md b/preprocessors/Emilia/README.md index d5654d82..e34220ee 100644 --- a/preprocessors/Emilia/README.md +++ b/preprocessors/Emilia/README.md @@ -6,6 +6,7 @@ This is the official repository πŸ‘‘ for the **Emilia** dataset and the source c
## News πŸ”₯ +- **2024/09/01**: [Emilia](https://arxiv.org/abs/2407.05361) got accepted by IEEE SLT 2024! πŸ€— - **2024/08/28**: Welcome to join Amphion's [Discord channel](https://discord.com/invite/ZxxREr3Y) to stay connected and engage with our community! - **2024/08/27**: *The Emilia dataset is now publicly available!* Discover the most extensive and diverse speech generation dataset with 101k hours of in-the-wild speech data now at [![hf](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Dataset-yellow)](https://huggingface.co/datasets/amphion/Emilia-Dataset) or [![OpenDataLab](https://img.shields.io/badge/OpenDataLab-Dataset-blue)](https://opendatalab.com/Amphion/Emilia)! πŸ‘‘πŸ‘‘πŸ‘‘ - **2024/07/08**: Our preprint [paper](https://arxiv.org/abs/2407.05361) is now available! πŸ”₯πŸ”₯πŸ”₯ @@ -197,20 +198,18 @@ We acknowledge the wonderful work by these excellent developers! ## Reference πŸ“– If you use the Emilia dataset or the Emilia-Pipe pipeline, please cite the following papers: ```bibtex -@article{emilia, - title={Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation}, - author={He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng}, - journal={arXiv}, - volume={abs/2407.05361}, - year={2024} +@inproceedings{emilia, + author={He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng}, + title={Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation}, + booktitle={Proc.~of SLT}, + year={2024} } ``` ```bibtex -@article{amphion, - title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit}, - author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and He, Haorui and Wang, Chaoren and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng}, - journal={arXiv}, - volume={abs/2312.09911}, - year={2024}, +@inproceedings{amphion, + author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and Li, Jiaqi and He, Haorui and Wang, Chaoren and Song, Ting and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng}, + title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit}, + booktitle={Proc.~of SLT}, + year={2024} } ```