UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner

TL;DR

UniAudio 1.5 introduces a novel LLM-driven audio codec enabling large language models to perform multiple audio tasks in a few-shot manner without fine-tuning, by translating audio into a textual token space.

Contribution

The paper presents LLM-Codec, a new method to convert audio into a text-like token space for LLMs, enabling cross-modal few-shot learning for audio tasks.

Findings

Effective in multiple audio understanding tasks

Achieves good performance with few examples

Open-sourced LLM-Codec for research use

Abstract

The Large Language models (LLMs) have demonstrated supreme capabilities in text understanding and generation, but cannot be directly applied to cross-modal tasks without fine-tuning. This paper proposes a cross-modal in-context learning approach, empowering the frozen LLMs to achieve multiple audio tasks in a few-shot style without any parameter update. Specifically, we propose a novel and LLMs-driven audio codec model, LLM-Codec, to transfer the audio modality into the textual space, \textit{i.e.} representing audio tokens with words or sub-words in the vocabulary of LLMs, while keeping high audio reconstruction quality. The key idea is to reduce the modality heterogeneity between text and audio by compressing the audio modality into a well-trained LLMs token space. Thus, the audio representation can be viewed as a new \textit{foreign language}, and LLMs can learn the new \textit{foreign language} with several demonstrations. In experiments, we investigate the performance of the proposed approach across multiple audio understanding and generation tasks, \textit{e.g.} speech emotion classification, audio classification, text-to-speech generation, speech enhancement, etc. The experimental results demonstrate that the LLMs equipped with the proposed LLM-Codec, named as UniAudio 1.5, prompted by only a few examples, can achieve the expected functions in simple scenarios. It validates the feasibility and effectiveness of the proposed cross-modal in-context learning approach. To facilitate research on few-shot audio task learning and multi-modal LLMs, we have open-sourced the LLM-Codec model.