#MOVED TO: https://github.com/CarlWangChina/QwenFeat-Vocal-Score

📢 Project Update / 项目更新说明

English: Due to version management and ongoing updates, the code, data, and model weights for this project have been consolidated into a more frequently maintained repository. Please follow the links below for the latest resources:

中文: 由于版本维护和更新需要，本项目的代码、数据及模型权重已整合至统一的维护仓库中。请通过以下链接获取最新资源：

🔗 Resources / 资源链接

• Code Repository (GitHub): https://github.com/CarlWangChina/QwenFeat-Vocal-Score/tree/master
• Model Weights (Hugging Face): https://huggingface.co/karl-wang/QwenFeat-Vocal-Score/tree/main/qwenaudio/ckpts
  • You can also clone the entire weights repository via: git clone https://huggingface.co/karl-wang/QwenFeat-Vocal-Score

---

📄 License & Copyright / 开源协议与版权

Copyright (c) 2025 [The Project Author(s)]. All rights reserved.

1. License Model: This project is licensed under the CC BY-NC-ND 4.0 (Attribution-NonCommercial-NoDerivatives 4.0 International).
2. Usage: Code and weights are for academic and educational use only.
3. Commercial Restrictions: Commercial use is STRICTLY PROHIBITED without written authorization. This includes integration into commercial software or for-profit AI services.
4. Inquiries: For commercial licensing, please contact: 3156018231@qq.com.

中文摘要：

1. 协议框架：本项目采用 CC BY-NC-ND 4.0 (署名-非商业性使用-禁止演绎) 国际许可协议。
2. 严禁商用：未经授权，严禁将本项目任何部分用于商业盈利目的。
3. 授权联系：如有商业合作意向，请务必联系邮箱：3156018231@qq.com。

---

📖 论文引用与说明

关于本代码实现的详细技术方案、实验结果及理论支撑，请参考我们的研究论文。如果您在研究或工作中使用了本仓库的代码或模型，欢迎引用我们的论文。

论文信息

标题：Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model 会议：Proceedings of the 33rd ACM International Conference on Multimedia (MM '25)

• ACM Digital Library (官方版本): https://doi.org/10.1145/3746027.3758148
• arXiv (免费预览版): https://www.arxiv.org/abs/2512.06999 (注：arXiv 版本内容与 ACM DL 官方版本完全一致)

引用格式

ACM Reference Format

Zihao Wang, Ruibin Yuan, Ziqi Geng, Hengjia Li, Xingwei Qu, Xinyi Li, Songye Chen, Haoying Fu, Roger B. Dannenberg, and Kejun Zhang. 2025. Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model. In Proceedings of the 33rd ACM International Conference on Multimedia (MM '25). Association for Computing Machinery, New York, NY, USA, 12227–12236. https://doi.org/10.1145/3746027.3758148

BibTeX

@inproceedings{10.1145/3746027.3758148,
author = {Wang, Zihao and Yuan, Ruibin and Geng, Ziqi and Li, Hengjia and Qu, Xingwei and Li, Xinyi and Chen, Songye and Fu, Haoying and Dannenberg, Roger B. and Zhang, Kejun},
title = {Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model},
year = {2025},
isbn = {9798400720352},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {[https://doi.org/10.1145/3746027.3758148](https://doi.org/10.1145/3746027.3758148)},
doi = {10.1145/3746027.3758148},
booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
pages = {12227–12236},
numpages = {10},
keywords = {computational music aesthetics, descriptive feedback, multi-dimensional evaluation, multimodal foundation models, singing timbre popularity, singing voice assessment},
location = {Dublin, Ireland},
series = {MM '25}
}