# Towards Weakly Supervised Text-to-Audio Grounding

arXiv: https://arxiv.org/abs/2401.02584 · HTML: https://mlsanity.com/paper/2401.02584/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2024.

## Built on by (most cited first, 9 of 9)

- [FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation](https://mlsanity.com/paper/2507.08557/) (2025)
- [Dissecting Temporal Understanding in Text-to-Audio Retrieval](https://mlsanity.com/paper/2409.00851/) (2024)
- [Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance](https://mlsanity.com/paper/2412.18157/) (2024)
- [Spatial Audio Question Answering and Reasoning on Dynamic Source Movements](https://mlsanity.com/paper/2602.16334/) (2026)
- [Spatial Audio Motion Understanding and Reasoning](https://mlsanity.com/paper/2509.14666/) (2025)
- [Event-Grounded Question Answering over Long Audio via Structured Retrieval](https://mlsanity.com/paper/2602.14612/) (2026)
- [FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts](https://mlsanity.com/paper/2603.19857/) (2026)
- [M3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation](https://mlsanity.com/paper/2512.20136/) (2025)
- [Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding](https://mlsanity.com/paper/2607.04383/) (2026)

## Abstract (arXiv)

Text-to-audio grounding (TAG) task aims to predict the onsets and offsets of sound events described by natural language. This task can facilitate applications such as multimodal information retrieval. This paper focuses on weakly-supervised text-to-audio grounding (WSTAG), where frame-level annotations of sound events are unavailable, and only the caption of a whole audio clip can be utilized for training. WSTAG is superior to strongly-supervised approaches in its scalability to large audio-text datasets. Two WSTAG frameworks are studied in this paper: sentence-level and phrase-level. First, we analyze the limitations of mean pooling used in the previous WSTAG approach and investigate the effects of different pooling strategies. We then propose phrase-level WSTAG to use matching labels between audio clips and phrases for training. Advanced negative sampling strategies and self-supervision are proposed to enhance the accuracy of the weak labels and provide pseudo strong labels. Experimental results show that our system significantly outperforms the previous WSTAG SOTA. Finally, we conduct extensive experiments to analyze the effects of several factors on phrase-level WSTAG. The code and model is available at https://github.com/wsntxxn/TextToAudioGrounding.