AudioLog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning

TL;DR

AudioLog introduces a novel LLM-powered system with hybrid contrastive learning for long audio logging, significantly improving scene and event detection while effectively summarizing lengthy audio sequences.

Contribution

This work is the first to leverage large language models for summarizing long audio sequences using a hybrid token-semantic contrastive learning approach.

Findings

Outperforms existing methods in scene classification

Achieves superior sound event detection accuracy

Effectively summarizes long audio sequences

Abstract

Previous studies in automated audio captioning have faced difficulties in accurately capturing the complete temporal details of acoustic scenes and events within long audio sequences. This paper presents AudioLog, a large language models (LLMs)-powered audio logging system with hybrid token-semantic contrastive learning. Specifically, we propose to fine-tune the pre-trained hierarchical token-semantic audio Transformer by incorporating contrastive learning between hybrid acoustic representations. We then leverage LLMs to generate audio logs that summarize textual descriptions of the acoustic environment. Finally, we evaluate the AudioLog system on two datasets with both scene and event annotations. Experiments show that the proposed system achieves exceptional performance in acoustic scene classification and sound event detection, surpassing existing methods in the field. Further analysis of the prompts to LLMs demonstrates that AudioLog can effectively summarize long audio sequences. To the best of our knowledge, this approach is the first attempt to leverage LLMs for summarizing long audio sequences.