A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restoration
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908876351209472 |
|---|---|
| author | Lay, Bunlong Gerkmann, Timo |
| author_facet | Lay, Bunlong Gerkmann, Timo |
| contents | Diffusion Probabilistic Models (DPMs) are a well-established class of diffusion models for unconditional image generation, while SGMSE+ is a well-established conditional diffusion model for speech enhancement. One of the downsides of diffusion models is that solving the reverse process requires many evaluations of a large Neural Network. Although advanced fast sampling solvers have been developed for DPMs, they are not directly applicable to models such as SGMSE+ due to differences in their diffusion processes. Specifically, DPMs transform between the data distribution and a standard Gaussian distribution, whereas SGMSE+ interpolates between the target distribution and a noisy observation. This work first develops a formalism of interpolating Stochastic Differential Equations (iSDEs) that includes SGMSE+, and second proposes a solver for iSDEs. The proposed solver enables fast sampling with as few as 10 Neural Network evaluations across multiple speech restoration tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09508 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restoration Lay, Bunlong Gerkmann, Timo Audio and Speech Processing Diffusion Probabilistic Models (DPMs) are a well-established class of diffusion models for unconditional image generation, while SGMSE+ is a well-established conditional diffusion model for speech enhancement. One of the downsides of diffusion models is that solving the reverse process requires many evaluations of a large Neural Network. Although advanced fast sampling solvers have been developed for DPMs, they are not directly applicable to models such as SGMSE+ due to differences in their diffusion processes. Specifically, DPMs transform between the data distribution and a standard Gaussian distribution, whereas SGMSE+ interpolates between the target distribution and a noisy observation. This work first develops a formalism of interpolating Stochastic Differential Equations (iSDEs) that includes SGMSE+, and second proposes a solver for iSDEs. The proposed solver enables fast sampling with as few as 10 Neural Network evaluations across multiple speech restoration tasks. |
| title | A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restoration |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.09508 |