Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Chao-Han Huck, Ghosh, Sreyan, Wang, Qing, Kim, Jaeyeon, Hong, Hengyi, Kumar, Sonal, Zhong, Guirui, Kong, Zhifeng, Sakshi, S, Lokegaonkar, Vaibhavi, Nieto, Oriol, Duraiswami, Ramani, Manocha, Dinesh, Kim, Gunhee, Du, Jun, Valle, Rafael, Catanzaro, Bryan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2505.07365
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910045472555008
author Yang, Chao-Han Huck
Ghosh, Sreyan
Wang, Qing
Kim, Jaeyeon
Hong, Hengyi
Kumar, Sonal
Zhong, Guirui
Kong, Zhifeng
Sakshi, S
Lokegaonkar, Vaibhavi
Nieto, Oriol
Duraiswami, Ramani
Manocha, Dinesh
Kim, Gunhee
Du, Jun
Valle, Rafael
Catanzaro, Bryan
author_facet Yang, Chao-Han Huck
Ghosh, Sreyan
Wang, Qing
Kim, Jaeyeon
Hong, Hengyi
Kumar, Sonal
Zhong, Guirui
Kong, Zhifeng
Sakshi, S
Lokegaonkar, Vaibhavi
Nieto, Oriol
Duraiswami, Ramani
Manocha, Dinesh
Kim, Gunhee
Du, Jun
Valle, Rafael
Catanzaro, Bryan
contents We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding. This task defines three QA subsets (Bioacoustics, Temporal Soundscapes, and Complex QA) to test audio-language models on interactive question-answering over diverse acoustic scenes. We describe the dataset composition (from marine mammal calls to soundscapes and complex real-world clips), the evaluation protocol (top-1 accuracy with answer-shuffling robustness), and baseline systems (Qwen2-Audio-7B, AudioFlamingo 2, Gemini-2-Flash). Preliminary results on the development set are compared, showing strong variation across models and subsets. This challenge aims to advance the audio understanding and reasoning capabilities of audio-language models toward human-level acuity, which are crucial for enabling AI agents to perceive and interact about the world effectively.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07365
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning
Yang, Chao-Han Huck
Ghosh, Sreyan
Wang, Qing
Kim, Jaeyeon
Hong, Hengyi
Kumar, Sonal
Zhong, Guirui
Kong, Zhifeng
Sakshi, S
Lokegaonkar, Vaibhavi
Nieto, Oriol
Duraiswami, Ramani
Manocha, Dinesh
Kim, Gunhee
Du, Jun
Valle, Rafael
Catanzaro, Bryan
Sound
Artificial Intelligence
Computation and Language
Multimedia
Audio and Speech Processing
We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding. This task defines three QA subsets (Bioacoustics, Temporal Soundscapes, and Complex QA) to test audio-language models on interactive question-answering over diverse acoustic scenes. We describe the dataset composition (from marine mammal calls to soundscapes and complex real-world clips), the evaluation protocol (top-1 accuracy with answer-shuffling robustness), and baseline systems (Qwen2-Audio-7B, AudioFlamingo 2, Gemini-2-Flash). Preliminary results on the development set are compared, showing strong variation across models and subsets. This challenge aims to advance the audio understanding and reasoning capabilities of audio-language models toward human-level acuity, which are crucial for enabling AI agents to perceive and interact about the world effectively.
title Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning
topic Sound
Artificial Intelligence
Computation and Language
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2505.07365