Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models

Yiming Chen, Xianghu Yue, Xiaoxue Gao, Chen Zhang, Luis Fernando D’Haro, Robby T. Tan, Haizhou Li


Abstract
Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audio elements in individual audio inputs, struggling to handle multi-audio scenarios. To this end, we propose a novel multi-audio-LLM (MALLM) to capture audio context among multiple similar audios using discriminative learning on our proposed synthetic data. The results demonstrate that the proposed MALLM outperforms all baselines and achieves high data efficiency using synthetic data without requiring human annotations. The proposed MALLM opens the door for ALLMs towards multi-audio processing era and brings us closer to replicating human auditory capabilities in machines.
Anthology ID:
2024.findings-emnlp.640
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10917–10930
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.640/
DOI:
10.18653/v1/2024.findings-emnlp.640
Bibkey:
Cite (ACL):
Yiming Chen, Xianghu Yue, Xiaoxue Gao, Chen Zhang, Luis Fernando D’Haro, Robby T. Tan, and Haizhou Li. 2024. Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10917–10930, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models (Chen et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.640.pdf