English

AC/DC: LLM-based Audio Comprehension via Dialogue Continuation

Audio and Speech Processing 2025-06-13 v1 Computation and Language Sound

Abstract

We propose an instruction-following audio comprehension model that leverages the dialogue continuation ability of large language models (LLMs). Instead of directly generating target captions in training data, the proposed method trains a model to produce responses as if the input caption triggered a dialogue. This dialogue continuation training mitigates the caption variation problem. Learning to continue a dialogue effectively captures the caption's meaning beyond its surface-level words. As a result, our model enables zero-shot instruction-following capability without multitask instruction tuning, even trained solely on audio captioning datasets. Experiments on AudioCaps, WavCaps, and Clotho datasets with AudioBench audio-scene question-answering tests demonstrate our model's ability to follow various unseen instructions.

Keywords

Cite

@article{arxiv.2506.10312,
  title  = {AC/DC: LLM-based Audio Comprehension via Dialogue Continuation},
  author = {Yusuke Fujita and Tomoya Mizumoto and Atsushi Kojima and Lianbo Liu and Yui Sudo},
  journal= {arXiv preprint arXiv:2506.10312},
  year   = {2025}
}

Comments

Accepted to Interspeech 2025

R2 v1 2026-07-01T03:12:26.840Z