Virtual Consistency for Audio Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912598554836992 |
|---|---|
| author | Cervera, Matthieu Paissan, Francesco Ravanelli, Mirco Subakan, Cem |
| author_facet | Cervera, Matthieu Paissan, Francesco Ravanelli, Mirco Subakan, Cem |
| contents | Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Virtual Consistency for Audio Editing Cervera, Matthieu Paissan, Francesco Ravanelli, Mirco Subakan, Cem Sound Machine Learning Free-form, text-based audio editing remains a persistent challenge, despite progress in inversion-based neural methods. Current approaches rely on slow inversion procedures, limiting their practicality. We present a virtual-consistency based audio editing system that bypasses inversion by adapting the sampling process of diffusion models. Our pipeline is model-agnostic, requiring no fine-tuning or architectural changes, and achieves substantial speed-ups over recent neural editing baselines. Crucially, it achieves this efficiency without compromising quality, as demonstrated by quantitative benchmarks and a user study involving 16 participants. |
| title | Virtual Consistency for Audio Editing |
| topic | Sound Machine Learning |
| url | https://arxiv.org/abs/2509.17219 |