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

arXiv: https://arxiv.org/abs/2503.16853 · HTML: https://mlsanity.com/paper/2503.16853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision](https://mlsanity.com/paper/2010.06775/) (2020)
- [TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization](https://mlsanity.com/paper/2412.21037/) (2024)
- [Things not Written in Text: Exploring Spatial Commonsense from Visual Signals](https://mlsanity.com/paper/2203.08075/) (2022)
- [Visual Commonsense in Pretrained Unimodal and Multimodal Models](https://mlsanity.com/paper/2205.01850/) (2022)
- [Is BERT Blind? Exploring the Effect of Vision-and-Language Pretraining on Visual Language Understanding](https://mlsanity.com/paper/2303.12513/) (2023)
- [What Do Language Models Hear? Probing for Auditory Representations in Language Models](https://mlsanity.com/paper/2402.16998/) (2024)
- [Visually-augmented pretrained language models for NLP tasks without images](https://mlsanity.com/paper/2212.07937/) (2022)

## Built on by (most cited first, 2 of 2)

- [How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation](https://mlsanity.com/paper/2603.19195/) (2026)
- [AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?](https://mlsanity.com/paper/2509.17641/) (2025)

## Abstract (arXiv)

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 language-audio 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.