Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Trachu, Thanapat, Piansaddhayanon, Chawan, Chuangsuwanich, Ekapol
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909220295671808
author Trachu, Thanapat
Piansaddhayanon, Chawan
Chuangsuwanich, Ekapol
author_facet Trachu, Thanapat
Piansaddhayanon, Chawan
Chuangsuwanich, Ekapol
contents Diffusion-based speech enhancement has shown promising results, but can suffer from a slower inference time. Initializing the diffusion process with the enhanced audio generated by a regression-based model can be used to reduce the computational steps required. However, these approaches often necessitate a regression model, further increasing the system's complexity. We propose Thunder, a unified regression-diffusion model that utilizes the Brownian bridge process which can allow the model to act in both modes. The regression mode can be accessed by setting the diffusion time step closed to 1. However, the standard score-based diffusion modeling does not perform well in this setup due to gradient instability. To mitigate this problem, we modify the diffusion model to predict the clean speech instead of the score function, achieving competitive performance with a more compact model size and fewer reverse steps.
format Preprint
id arxiv_https___arxiv_org_abs_2406_06139
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge
Trachu, Thanapat
Piansaddhayanon, Chawan
Chuangsuwanich, Ekapol
Sound
Artificial Intelligence
Computation and Language
Audio and Speech Processing
Diffusion-based speech enhancement has shown promising results, but can suffer from a slower inference time. Initializing the diffusion process with the enhanced audio generated by a regression-based model can be used to reduce the computational steps required. However, these approaches often necessitate a regression model, further increasing the system's complexity. We propose Thunder, a unified regression-diffusion model that utilizes the Brownian bridge process which can allow the model to act in both modes. The regression mode can be accessed by setting the diffusion time step closed to 1. However, the standard score-based diffusion modeling does not perform well in this setup due to gradient instability. To mitigate this problem, we modify the diffusion model to predict the clean speech instead of the score function, achieving competitive performance with a more compact model size and fewer reverse steps.
title Thunder : Unified Regression-Diffusion Speech Enhancement with a Single Reverse Step using Brownian Bridge
topic Sound
Artificial Intelligence
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2406.06139