I'll Keep an Ear Out: Teaching AudioLLMs Proactive Audio Assistance
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The Flow has not summarised this story yet — read it at arXiv Computation and Language.
arXiv:2606. 05121v1 Announce Type: cross Abstract: Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single task such as streaming ASR or voice chatting.
arXiv:2609.36577v1 Announce Type: cross Abstract: Audio large language models (ALLMs) can reason about the content of audio recordings to perform complex tasks. However, these capabilities usually co...
arXiv:2606. 11400v1 Announce Type: cross Abstract: Large Audio-Language Models (LALMs) excel at audio understanding but expose little about where in an audio signal they attend.
arXiv:2609.20995v1 Announce Type: cross Abstract: Natural spoken interaction requires more than streaming ASR, language generation, and speech synthesis: a system must react to overlap without cancel...
AudioTETRIS is a training‑free, two‑stage token elimination framework designed for large audio language models. It leverages the geometry of audio encoder representations as an acoustic prior to compute per‑token importance scores, which guide progressive top‑k token selection across decoder layers. Experiments on Qwen2‑Audio‑7B, Phi‑4‑Multimodal, and Audio Flamingo 3 show that AudioTETRIS retains near‑full performance while using only 25% of audio tokens and outperforms existing training‑free baselines.
The paper investigates how to evaluate audio‑language models by separating the use of acoustic evidence from the need to invoke a generative audio model. Using a controlled call‑decision framework, the authors compare policies that rely on transcript labels, encoder outputs from CLAP, AST, or WavLM, and optional calls to generative models such as Qwen2‑Audio, Qwen2.5‑Omni, or MOSS‑Audio. Results on the VocalSound dataset show that while transcript‑only accuracy is low (0.296), encoder‑only controls achieve high accuracy (≈0.85) without any generative calls, and adding generative calls yields only a marginal improvement (0.925 vs. 0.921).