# AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations

arXiv: https://arxiv.org/abs/2405.11093 · HTML: https://mlsanity.com/paper/2405.11093/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 17 May 2024.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/1912.10211/) (2019)
- [Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models](https://mlsanity.com/paper/2301.12661/) (2023)
- [Diffsound: Discrete Diffusion Model for Text-to-sound Generation](https://mlsanity.com/paper/2207.09983/) (2022)
- [The Benefit Of Temporally-Strong Labels In Audio Event Classification](https://mlsanity.com/paper/2105.07031/) (2021)
- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [Generating Visually Aligned Sound from Videos](https://mlsanity.com/paper/2008.00820/) (2020)
- [Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics](https://mlsanity.com/paper/2110.01518/) (2021)
- [Audio Retrieval with Natural Language Queries: A Benchmark Study](https://mlsanity.com/paper/2112.09418/) (2021)
- [Test of Time: Instilling Video-Language Models with a Sense of Time](https://mlsanity.com/paper/2301.02074/) (2023)
- [Large-scale representation learning from visually grounded untranscribed speech](https://mlsanity.com/paper/1909.08782/) (2019)
- [What is the ground truth? Reliability of multi-annotator data for audio tagging](https://mlsanity.com/paper/2104.04214/) (2021)
- [Audio-Text Models Do Not Yet Leverage Natural Language](https://mlsanity.com/paper/2303.10667/) (2023)
- [Automated Audio Captioning: An Overview of Recent Progress and New Challenges](https://mlsanity.com/paper/2205.05949/) (2022)

## Abstract (arXiv)

Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Existing audio-language datasets are notably smaller, and manual labeling is hindered by the need to listen to entire audio clips for accurate labeling. Our method systematically generates audio-caption pairs by augmenting audio clips with natural language labels and corresponding audio signal processing operations. Leveraging a Large Language Model, we generate descriptions of augmented audio clips with a prompt template. This scalable method produces AudioSetMix, a high-quality training dataset for text-and-audio related models. Integration of our dataset improves models performance on benchmarks by providing diversified and better-aligned examples. Notably, our dataset addresses the absence of modifiers (adjectives and adverbs) in existing datasets. By enabling models to learn these concepts, and generating hard negative examples during training, we achieve state-of-the-art performance on multiple benchmarks.