Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
This work addresses the modality gap problem for researchers and practitioners in audio-language AI, offering a novel diffusion-based approach that improves coupling between multimodal encoders and large language models, though it is incremental as it builds on prior diffusion methods.
The paper tackles the audio-text modality gap in multimodal models by introducing Diffusion-Link, a diffusion-based module that maps audio embeddings into the text-embedding distribution, achieving state-of-the-art results in Automatic Audio Captioning with relative gains up to 52.5% in zero-shot and 7.5% in fully supervised settings.
Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Diffusion-Link, a diffusion-based modality-bridging module that generatively maps audio embeddings into the text-embedding distribution. The module is trained at the output embedding from the frozen multimodal encoder and implemented as a lightweight network with three residual MLP blocks. To assess the effect of Diffusion-Link on multimodal encoder-LLM coupling, we evaluate on Automatic Audio Captioning (AAC); to our knowledge, this is the first application of diffusion-based modality bridging to AAC. We report two results. (1) Modality-gap analysis: on similarity and geometric criteria, Diffusion-Link reduces the modality gap the most among prior diffusion-based methods and shows a collective migration of audio embeddings toward the text distribution. (2) Downstream AAC: attaching Diffusion-Link to the same multimodal LLM baseline achieves state-of-the-art on AudioCaps in both zero-shot and fully supervised captioning without external knowledge, with relative gains up to 52.5% and 7.5%, respectively. These findings show that closing the modality gap is pivotal for effective coupling between multimodal encoders and LLMs, and diffusion-based modality bridging offers a promising direction beyond knowledge-retrieval-centric designs. Code will be released upon acceptance https://github.com/DevKiHyun/Diffusion-Link