# Audio ControlNet for Fine-Grained Audio Generation and Editing

arXiv: https://arxiv.org/abs/2602.04680 · HTML: https://mlsanity.com/paper/2602.04680/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 23 of 23)

- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining](https://mlsanity.com/paper/2308.05734/) (2023)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [ControlNeXt: Powerful and Efficient Control for Image and Video Generation](https://mlsanity.com/paper/2408.06070/) (2024)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [Audiobox: Unified Audio Generation with Natural Language Prompts](https://mlsanity.com/paper/2312.15821/) (2023)
- [LP-MusicCaps: LLM-Based Pseudo Music Captioning](https://mlsanity.com/paper/2307.16372/) (2023)
- [Music ControlNet: Multiple Time-varying Controls for Music Generation](https://mlsanity.com/paper/2311.07069/) (2023)
- [TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization](https://mlsanity.com/paper/2412.21037/) (2024)
- [EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer](https://mlsanity.com/paper/2409.10819/) (2024)
- [FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation](https://mlsanity.com/paper/2507.08557/) (2025)
- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation](https://mlsanity.com/paper/2407.02869/) (2024)
- [ControlAudio: Tackling Text-Guided, Timing-Indicated and Intelligible Audio Generation via Progressive Diffusion Modeling](https://mlsanity.com/paper/2510.08878/) (2025)
- [MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners](https://mlsanity.com/paper/2506.18729/) (2025)
- [AudioComposer: Towards Fine-grained Audio Generation with Natural Language Descriptions](https://mlsanity.com/paper/2409.12560/) (2024)
- [LiLAC: A Lightweight Latent ControlNet for Musical Audio Generation](https://mlsanity.com/paper/2506.11476/) (2025)
- [PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description](https://mlsanity.com/paper/2509.00683/) (2025)
- [Recomposer: Event-roll-guided generative audio editing](https://mlsanity.com/paper/2509.05256/) (2025)

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

- [AVControl: Efficient Framework for Training Audio-Visual Controls](https://mlsanity.com/paper/2603.24793/) (2026)
- [RFM-Editing 2: Text-Guided Audio Editing with Rectified Flow Matching and Coarse-to-Fine Diffusion Transformers](https://mlsanity.com/paper/2606.20101/) (2026)

## Abstract (arXiv)

We study the fine-grained text-to-audio (T2A) generation task. While recent models can synthesize high-quality audio from text descriptions, they often lack precise control over attributes such as loudness, pitch, and sound events. Unlike prior approaches that retrain models for specific control types, we propose to train ControlNet models on top of pre-trained T2A backbones to achieve controllable generation over loudness, pitch, and event roll. We introduce two designs, T2A-ControlNet and T2A-Adapter, and show that the T2A-Adapter model offers a more efficient structure with strong control ability. With only 38M additional parameters, T2A-Adapter achieves state-of-the-art performance on the AudioSet-Strong in both event-level and segment-level F1 scores. We further extend this framework to audio editing, proposing T2A-Editor for removing and inserting audio events at time locations specified by instructions. Models, code, dataset pipelines, and benchmarks will be released to support future research on controllable audio generation and editing.