EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing
EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing
In this study, we investigate leveraging cross-attention control for efficient audio editing within auto-regressive models. Inspired by image editing methodologies, we develop a Prompt-to-Prompt-like approach that guides edits through cross and self-attention mechanisms. Integrating a diffusion-based strategy, influenced by Auffusion, we extend the model's functionality to support refinement edits, establishing a baseline for prompt-guided audio editing. Additionally, we introduce an alternative approach by incorporating MUSICGEN, a pre-trained frozen auto-regressive model, and propose three editing mechanisms, based on Replacement, Reweighting, and Refinement of the attention scores. We employ commonly-used music-specific evaluation metrics and a human study, to gauge time-varying controllability, adherence to global text cues, and overall audio realism. The automatic and human evaluations indicate that the proposed combination of prompt-to-prompt guidance with autoregressive generation models significantly outperforms the diffusion-based baseline in terms of melody, dynamics, and tempo of the generated audio. Our code is available at https://github.com/billsioros/EditGen
Vassilis Sioros、Alexandros Potamianos、Giorgos Paraskevopoulos
计算技术、计算机技术
Vassilis Sioros,Alexandros Potamianos,Giorgos Paraskevopoulos.EditGen: Harnessing Cross-Attention Control for Instruction-Based Auto-Regressive Audio Editing[EB/OL].(2025-07-15)[2025-07-25].https://arxiv.org/abs/2507.11096.点此复制
评论