20 results for “AudioLLMs”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Proactive audio assistance for Deaf and Hard of Hearing users
The authors present a system design case study for a scalable, low-cost, and offline evaluation pipeline for synthetic speech quality.
Jisu Jeon, Seungyeon Jwa, Joosung Lee, Jinhyeon Kim +5 more
This paper introduces ParaPairAudioBench, a benchmark for evaluating the reliability of Large Audio-Language Models (LALMs) in paralinguistic speech evaluation.
Yanyun Wang, Yu Huang, Zi Liang, Xixin Wu +1 more
The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…
Meng Chen, Kun Wang, Li Lu, Jiaheng Zhang +1 more
The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models c…
This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…
Xiaoyu Yang, Xuenan Xu, Wenyi Yu, Siyin Wang +9 more
The paper proposes SALMONN-2, an ALLM built on a unified SSL encoder, and presents a multi-layer feature fusion adapter to better exploit hierarchical SSL encoder representations. It also explores mul…
Huadai Liu, Kaicheng Luo, Wen Wang, Qian Chen +3 more
This paper presents AudioCALM, a universal audio generation framework that unifies speech, sound, and music generation.
Zhisheng Zhang, Xiang Li, Yixuan Zhou, Jing Peng +2 more
LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and effi…
Naijun Zheng, Yuke Lin, Sanli Tian, Mengtian Li +3 more
The paper proposes strategies to efficiently train an LLM-based system for multi-talker speech recognition with limited data.