Update README.md
Browse files
README.md
CHANGED
|
@@ -27,20 +27,22 @@ tags:
|
|
| 27 |
|
| 28 |
<div align="center">
|
| 29 |
<h3>
|
| 30 |
-
Chunbo Hao<sup>1*</sup>, Ruibin Yuan<sup>2,
|
| 31 |
</h3>
|
| 32 |
-
|
|
|
|
| 33 |
<p>
|
| 34 |
<sup>*</sup>Equal contribution <sup>†</sup>Corresponding author
|
| 35 |
</p>
|
| 36 |
-
|
| 37 |
<p>
|
| 38 |
-
<sup>1</sup>Audio, Speech and Language Processing Group (ASLP@NPU),<br>Northwestern Polytechnical University<br>
|
| 39 |
<sup>2</sup>Hong Kong University of Science and Technology<br>
|
| 40 |
<sup>3</sup>Northwestern University<br>
|
| 41 |
<sup>4</sup>Cornell University<br>
|
| 42 |
-
<sup>5</sup>
|
|
|
|
| 43 |
</p>
|
|
|
|
| 44 |
</div>
|
| 45 |
|
| 46 |
----
|
|
@@ -173,13 +175,13 @@ The model returns a structured list of segment predictions, with each entry cont
|
|
| 173 |
If you use **SongFormer** in your research or application, please cite our work:
|
| 174 |
|
| 175 |
```bibtex
|
| 176 |
-
@misc{
|
| 177 |
-
|
| 178 |
-
|
| 179 |
-
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
}
|
| 185 |
```
|
|
|
|
| 27 |
|
| 28 |
<div align="center">
|
| 29 |
<h3>
|
| 30 |
+
Chunbo Hao<sup>1*</sup>, Ruibin Yuan<sup>2,6*</sup>, Jixun Yao<sup>1</sup>, Qixin Deng<sup>3,6</sup>,<br>Xinyi Bai<sup>4,6</sup>, Yanbo Wang<sup>5</sup>, Wei Xue<sup>2</sup>, Lei Xie<sup>1†</sup>
|
| 31 |
</h3>
|
| 32 |
+
|
| 33 |
+
|
| 34 |
<p>
|
| 35 |
<sup>*</sup>Equal contribution <sup>†</sup>Corresponding author
|
| 36 |
</p>
|
|
|
|
| 37 |
<p>
|
| 38 |
+
<sup>1</sup>Audio, Speech and Language Processing Group (ASLP@NPU),<br>School of Computer Science, Northwestern Polytechnical University<br>
|
| 39 |
<sup>2</sup>Hong Kong University of Science and Technology<br>
|
| 40 |
<sup>3</sup>Northwestern University<br>
|
| 41 |
<sup>4</sup>Cornell University<br>
|
| 42 |
+
<sup>5</sup>University of New South Wales<br>
|
| 43 |
+
<sup>6</sup>Multimodal Art Projection (M-A-P)
|
| 44 |
</p>
|
| 45 |
+
|
| 46 |
</div>
|
| 47 |
|
| 48 |
----
|
|
|
|
| 175 |
If you use **SongFormer** in your research or application, please cite our work:
|
| 176 |
|
| 177 |
```bibtex
|
| 178 |
+
@misc{hao2026songformerscalingmusicstructure,
|
| 179 |
+
title={SongFormer: Scaling Music Structure Analysis with Heterogeneous Supervision},
|
| 180 |
+
author={Chunbo Hao and Ruibin Yuan and Jixun Yao and Qixin Deng and Xinyi Bai and Yanbo Wang and Wei Xue and Lei Xie},
|
| 181 |
+
year={2026},
|
| 182 |
+
eprint={2510.02797},
|
| 183 |
+
archivePrefix={arXiv},
|
| 184 |
+
primaryClass={eess.AS},
|
| 185 |
+
url={https://arxiv.org/abs/2510.02797},
|
| 186 |
}
|
| 187 |
```
|