# Taming Data and Transformers for Audio Generation

arXiv: https://arxiv.org/abs/2406.19388 · HTML: https://mlsanity.com/paper/2406.19388/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 120 of its 165 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## Builds on (most cited first, 30 of 120)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)

## Built on by (most cited first, 28 of 28)

- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation](https://mlsanity.com/paper/2510.01284/) (2025)
- [HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation](https://mlsanity.com/paper/2508.16930/) (2025)
- [MOVA: Towards Scalable and Synchronized Video-Audio Generation](https://mlsanity.com/paper/2602.08794/) (2026)
- [EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer](https://mlsanity.com/paper/2409.10819/) (2024)
- [AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation](https://mlsanity.com/paper/2412.15191/) (2024)
- [ETTA: Elucidating the Design Space of Text-to-Audio Models](https://mlsanity.com/paper/2412.19351/) (2024)
- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [Improving Musical Accompaniment Co-creation via Diffusion Transformers](https://mlsanity.com/paper/2410.23005/) (2024)
- [Omni2Sound: Towards Unified Video-Text-to-Audio Generation](https://mlsanity.com/paper/2601.02731/) (2026)
- [Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers](https://mlsanity.com/paper/2510.04577/) (2025)
- [LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport](https://mlsanity.com/paper/2501.09291/) (2025)
- [Enhancing Retrieval-Augmented Audio Captioning with Generation-Assisted Multimodal Querying and Progressive Learning](https://mlsanity.com/paper/2410.10913/) (2024)
- [CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer](https://mlsanity.com/paper/2506.00800/) (2025)
- [AudioStory: Generating Long-Form Narrative Audio with Large Language Models](https://mlsanity.com/paper/2508.20088/) (2025)
- [Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding](https://mlsanity.com/paper/2601.14304/) (2026)
- [UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions](https://mlsanity.com/paper/2604.22209/) (2026)
- [WavFlow: Audio Generation in Waveform Space](https://mlsanity.com/paper/2605.18749/) (2026)
- [UNISON: A Unified Sound Generation and Editing Framework via Deep LLM Fusion](https://mlsanity.com/paper/2605.31530/) (2026)
- [Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning](https://mlsanity.com/paper/2502.05435/) (2025)
- [LAMB: LLM-based Audio Captioning with Modality Gap Bridging via Cauchy-Schwarz Divergence](https://mlsanity.com/paper/2601.04658/) (2026)
- [Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models](https://mlsanity.com/paper/2607.09091/) (2026)
- [Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr'echet Distance](https://mlsanity.com/paper/2503.21721/) (2025)
- [FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision](https://mlsanity.com/paper/2606.14049/) (2026)
- [Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies](https://mlsanity.com/paper/2607.08270/) (2026)
- [VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching](https://mlsanity.com/paper/2608.12951/) (2026)
- [UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation](https://mlsanity.com/paper/2609.28206/) (2026)

## Abstract (arXiv)

The scalability of ambient sound generators is hindered by data scarcity, insufficient caption quality, and limited scalability in model architecture. This work addresses these challenges by advancing both data and model scaling. First, we propose an efficient and scalable dataset collection pipeline tailored for ambient audio generation, resulting in AutoReCap-XL, the largest ambient audio-text dataset with over 47 million clips. To provide high-quality textual annotations, we propose AutoCap, a high-quality automatic audio captioning model. By adopting a Q-Former module and leveraging audio metadata, AutoCap substantially enhances caption quality, reaching a CIDEr score of 83.2, a 3.2% improvement over previous captioning models. Finally, we propose GenAu, a scalable transformer-based audio generation architecture that we scale up to 1.25B parameters. We demonstrate its benefits from data scaling with synthetic captions as well as model size scaling. When compared to baseline audio generators trained at similar size and data scale, GenAu obtains significant improvements of 4.7% in FAD score, 11.1% in IS, and 13.5% in CLAP score. Our code, model checkpoints, and dataset are publicly available.