Update README.md
Browse files
README.md
CHANGED
|
@@ -17,9 +17,9 @@ On our system, the performances obtained with our provided checkpoints are:
|
|
| 17 |
| Binaural Encoder | mAP (↑) | ER20° (↓) | MAE (↓) | DER (↓) |
|
| 18 |
| :---: | :---: | :---: | :---: | :---: |
|
| 19 |
| [SpatialAST](https://huggingface.co/datasets/zhisheng01/SpatialAudio/blob/main/SpatialAST/finetuned.pth) | 49.90 | 24.43 | 17.87 | 32.50 |
|
| 20 |
-
| DSpAST (stage 1) | 53.05 | 98.56 | 95.57 | 97.58 |
|
| 21 |
-
| DSpAST (stage 2) | 52.64 | 20.31 | **14.44** | 28.35 |
|
| 22 |
-
| DSpAST (stage 3) | **54.53** | **20.28** | **14.44** | **28.03** |
|
| 23 |
|
| 24 |
Similar performance improvements can also be observed when using DSpAST as a binaural encoder for spatial audio reasoning with LLMs. Please have a look at our [paper](https://arxiv.org/abs/2509.13927) for further information.
|
| 25 |
|
|
|
|
| 17 |
| Binaural Encoder | mAP (↑) | ER20° (↓) | MAE (↓) | DER (↓) |
|
| 18 |
| :---: | :---: | :---: | :---: | :---: |
|
| 19 |
| [SpatialAST](https://huggingface.co/datasets/zhisheng01/SpatialAudio/blob/main/SpatialAST/finetuned.pth) | 49.90 | 24.43 | 17.87 | 32.50 |
|
| 20 |
+
| [DSpAST (stage 1)](https://huggingface.co/kwilk90/DSpAST/blob/main/DSpAST-stage1) | 53.05 | 98.56 | 95.57 | 97.58 |
|
| 21 |
+
| [DSpAST (stage 2)](https://huggingface.co/kwilk90/DSpAST/blob/main/DSpAST-stage2) | 52.64 | 20.31 | **14.44** | 28.35 |
|
| 22 |
+
| [DSpAST (stage 3)](https://huggingface.co/kwilk90/DSpAST/blob/main/DSpAST-stage3) | **54.53** | **20.28** | **14.44** | **28.03** |
|
| 23 |
|
| 24 |
Similar performance improvements can also be observed when using DSpAST as a binaural encoder for spatial audio reasoning with LLMs. Please have a look at our [paper](https://arxiv.org/abs/2509.13927) for further information.
|
| 25 |
|