You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
title={An Embarrassingly Simple Approach for LLM with Strong ASR Capacity},
159
+
@article{ma2025speech,
160
+
title={Speech Recognition Meets Large Language Model: Benchmarking, Models, and Exploration},
161
161
author={Ma, Ziyang and Yang, Guanrou and Yang, Yifan and Gao, Zhifu and Wang, Jiaming and Du, Zhihao and Yu, Fan and Chen, Qian and Zheng, Siqi and Zhang, Shiliang and others},
162
-
journal={arXiv preprint arXiv:2402.08846},
163
-
year={2024}
162
+
journal={Proc. AAAI},
163
+
year={2025}
164
164
}
165
165
```
166
166
Mala-ASR:
@@ -181,23 +181,22 @@ LLM-Based Contextual ASR:
181
181
year={2024}
182
182
}
183
183
```
184
-
CoT-ST:
185
-
```
186
-
@article{du2024cot,
187
-
title={CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought},
188
-
author={Du, Yexing and Ma, Ziyang and Yang, Yifan and Deng, Keqi and Chen, Xie and Yang, Bo and Xiang, Yang and Liu, Ming and Qin, Bing},
189
-
journal={arXiv preprint arXiv:2409.19510},
190
-
year={2024}
191
-
}
192
-
```
193
-
194
184
SLAM-Omni:
195
185
```
196
186
@article{chen2024slam,
197
187
title={SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training},
198
188
author={Chen, Wenxi and Ma, Ziyang and Yan, Ruiqi and Liang, Yuzhe and Li, Xiquan and Xu, Ruiyang and Niu, Zhikang and Zhu, Yanqiao and Yang, Yifan and Liu, Zhanxun and others},
199
-
journal={arXiv preprint arXiv:2412.15649},
200
-
year={2024}
189
+
journal={Proc. ACL},
190
+
year={2025}
191
+
}
192
+
```
193
+
CoT-ST:
194
+
```
195
+
@article{du2024cot,
196
+
title={CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought},
197
+
author={Du, Yexing and Ma, Ziyang and Yang, Yifan and Deng, Keqi and Chen, Xie and Yang, Bo and Xiang, Yang and Liu, Ming and Qin, Bing},
0 commit comments