Work

Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models

Year: 2025

Type: conference-paper

Abstract: Language models pretrained on text-only corpora often struggle with tasks that require auditory commonsense knowledge.Previous work addresses this problem by augmenting the language model to retrieve knowledge from external audio databases.This approach has several limitations, such as the potential lack of relevant audio in databases and the high costs associated with constructing the databases.To address these issues, we propose Imagine to Hear, a novel approach that dynamically generates auditory knowledge using generative models.Our framework detects multiple audio-related textual spans from the given prompt and generates corresponding auditory knowledge.We develop several mechanisms to efficiently process multiple auditory knowledge, including a CLAP-based rejection sampler and a languageaudio fusion module.Our experiments show that our method achieves state-of-the-art performance on AuditoryBench without relying on external databases, highlighting the effectiveness of our generation-based approach.

DOI: 10.18653/v1/2025.findings-acl.730

Authors: Suho Yoo, Hyunjong Ok, Jaeho Lee

Institution: Pohang University of Science and Technology

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold