arXiv:2609.27389v1 Announce Type: cross
Abstract: Audio language models understand what is said far better than how it sounds. Closing this gap takes more than data. Detailed acoustic annotation is c...
By Yuxiang Wang, Shengbo Cai, Yingda Shen, Ming-Hao Hsu, Qinke Ni, Liqiang Zhang, Teddy Sun, Steve Yevs, Zhizheng Wu
arXiv:2609.39847v1 Announce Type: cross
Abstract: Audio language models (ALMs) are increasingly used for audio deepfake detection (ADD), yet existing benchmarks assess their verdicts or rationale pla...
By Rong Wan, Suliu Qin, Jiaxi Li, Wei Xie, Wenwu Wang, Xiaolong Han, Lu Yin, Xilu Wang
arXiv:2510.11454v2 Announce Type: replace-cross
Abstract: Recent advancements in large multimodal models (LMMs) have shown strong capabilities in audio understanding. However, most systems rely solel...
By Kuan-Yi Lee, Tsung-En Lin, Hung-Yi Lee
The paper introduces the LongAudioQA dataset to support long‑form audio meeting understanding, addressing the scarcity of task‑specific question answering data. It proposes the GRGA model, which represents heterogeneous audio features as a multi‑dimensional graph and employs an agent‑planning approach for retrieval and answer generation. The work aims to overcome acoustic information loss and limited long‑term context memory in existing speech QA methods and Speech LLMs.
By Quanwei Tang, Dong Zhang, Shoushan Li, Guodong Zhou
SpeechGym is an audio‑native environment that lets two omni‑modal models converse entirely in native audio, eliminating external ASR/TTS and API boundaries while preserving the tasks, tools, and success checks of a standard text‑based agent benchmark. By training end‑to‑end, the framework addresses perceptual failures—such as misheard arguments that cascade into failed calls—and behavioural failures, both of which are automatically labeled for free. Using per‑turn process rewards to overcome reward sparsity, agents trained in SpeechGym transfer to an independent voice benchmark, doubling task success and improving efficiency in turns and tokens.
By Jiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar, Jia-Hong Huang, Qi Luo, M. Maruf, Ivan Bulyko, Ge Liu, Roger Ren
arXiv:2609.37818v1 Announce Type: cross
Abstract: Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguis...
By Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang, Shun Lei, Di Cao, Teddy Sun, Zhiyong Wu