ACL Findings2026
Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation
Xiaoqian Liu, Zhengkun Ge, Jianjin Wang, Haoran Zhang, Yuan Ge, Kaiyan Chang, Chen Xu, Tong Xiao, Zhengtao Yu, Linfeng Zhang, JingBo Zhu
Abstract
Recent advancements in audio diffusion models have significantly improved text-to-audio editing via inversion techniques. However, these models typically rely on dense, fixedstep sampling trajectories to maintain structural integrity during inversion and generation, leading to prohibitive computational costs. We propose AdaTE, a model-agnostic Adaptive Trajectory Extrapolation framework that accelerates the inversion-based editing process by dynamically evaluating only the most critical generative phases. Specifically, we introduce a hierarchical probing mechanism that monitors curvature acceleration and information gain to detect pivotal transitions within the latent flow. This allows the model to selectively skip redundant segments via linear extrapolation while preserving dense neural evaluations for complex semantic changes. Extensive experiments across AudioLDM2, Auffusion, and Tango2 demonstrate that AdaTE achieves up to a 3.9ˆspeedup with negligible loss in fidelity. AdaTE significantly shifts the Pareto frontier, providing an efficient solution for high-fidelity audio synthesis and editing.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Consistency Models cites Denoising Diffusion Implicit Models
- Consistency Models cites DiffWave: A Versatile Diffusion Model for Audio Synthesis
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps cites Denoising Diffusion Implicit Models
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations cites Denoising Diffusion Implicit Models
Builds on19
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 StepsCheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen et al.NeurIPS 2022 · 2,653 citations
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsChenlin Meng, Yutong He, Yang Song, Jiaming Song et al.ICLR 2022 · 2,128 citations
- DiffWave: A Versatile Diffusion Model for Audio SynthesisZhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao et al.ICLR 2021 · 1,902 citations
- Consistency ModelsYang Song, Prafulla Dhariwal, Mark Chen, Ilya SutskeverICML 2023 · 1,720 citations
Related papers
- WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided ExtrapolationXiaoqian Liu, Xiyan Gui, Zhengkun Ge, Yuan Ge et al.AAAI 2026 · 1 citation
- Diffusion Adaptive Text Embedding for Text-to-Image Diffusion ModelsByeonghu Na, Minsang Park, Gyuwon Sim, Donghyeok Shin et al.NeurIPS 2025 · 8 citations
- IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion ModelingKuan-Po Huang, Shu-Wen Yang, Huy Phan, Bo-Ru Lu et al.ICML 2025
- Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion ModelsYi Yang, Haowen Li, Tianxiang Li, Boyu Cao et al.AAAI 2026 · 1 citation
- Text-to-Audio Generation using Instruction Guided Latent Diffusion ModelDeepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya PoriaACM MM 2023 · 90 citations
