Enregistré dans:
Détails bibliographiques
Auteurs principaux: Guo, Zhihan, Cui, Wenqian, Lin, Guan-Ting, Tan, Daxin, Li, Jingyao, Zheng, Qiyong, Wang, Dingdong, Xiong, Jing, Shi, Han, Jia, Jiaya, King, Irwin
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2605.21008
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916031057887232
author Guo, Zhihan
Cui, Wenqian
Lin, Guan-Ting
Tan, Daxin
Li, Jingyao
Zheng, Qiyong
Wang, Dingdong
Xiong, Jing
Shi, Han
Jia, Jiaya
King, Irwin
author_facet Guo, Zhihan
Cui, Wenqian
Lin, Guan-Ting
Tan, Daxin
Li, Jingyao
Zheng, Qiyong
Wang, Dingdong
Xiong, Jing
Shi, Han
Jia, Jiaya
King, Irwin
contents Reasoning has become a defining capability of modern foundation models, yet its development in the audio modality remains limited. Audio poses challenges that are distinct from those of text and vision. It is continuous, temporally dense, and contains linguistic, paralinguistic, and environmental information at multiple time scales. As a result, audio reasoning models must align acoustic signals with the discrete semantic space of large language models, while still preserving fine-grained information needed for reliable inference. Progress is also limited by three major obstacles: the scarcity of genuinely audio-grounded reasoning data, shortcut learning and modality hallucination, and the tension between reasoning depth and real-time latency in spoken interaction. In this paper, we present the first dedicated survey of audio reasoning. We provide a unified formulation that distinguishes direct predictive modeling from reasoning-augmented generation, review the architectural and training foundations of audio reasoning models, and systematically organize recent advances in Audio-to-Text, Audio-to-Speech, Audio-Visual Reasoning and Agentic Audio Reasoning. We further examine emerging paradigms such as Chain-of-Thought prompting, supervised fine-tuning, reinforcement learning, and latency-aware spoken interaction, and discuss evaluation practices, open challenges, and future directions. Our goal is to offer a coherent roadmap for developing robust, efficient, and natively grounded audio reasoning systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_21008
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Survey of Audio Reasoning in Multimodal Foundation Models
Guo, Zhihan
Cui, Wenqian
Lin, Guan-Ting
Tan, Daxin
Li, Jingyao
Zheng, Qiyong
Wang, Dingdong
Xiong, Jing
Shi, Han
Jia, Jiaya
King, Irwin
Audio and Speech Processing
Reasoning has become a defining capability of modern foundation models, yet its development in the audio modality remains limited. Audio poses challenges that are distinct from those of text and vision. It is continuous, temporally dense, and contains linguistic, paralinguistic, and environmental information at multiple time scales. As a result, audio reasoning models must align acoustic signals with the discrete semantic space of large language models, while still preserving fine-grained information needed for reliable inference. Progress is also limited by three major obstacles: the scarcity of genuinely audio-grounded reasoning data, shortcut learning and modality hallucination, and the tension between reasoning depth and real-time latency in spoken interaction. In this paper, we present the first dedicated survey of audio reasoning. We provide a unified formulation that distinguishes direct predictive modeling from reasoning-augmented generation, review the architectural and training foundations of audio reasoning models, and systematically organize recent advances in Audio-to-Text, Audio-to-Speech, Audio-Visual Reasoning and Agentic Audio Reasoning. We further examine emerging paradigms such as Chain-of-Thought prompting, supervised fine-tuning, reinforcement learning, and latency-aware spoken interaction, and discuss evaluation practices, open challenges, and future directions. Our goal is to offer a coherent roadmap for developing robust, efficient, and natively grounded audio reasoning systems.
title A Survey of Audio Reasoning in Multimodal Foundation Models
topic Audio and Speech Processing
url https://arxiv.org/abs/2605.21008