Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0197853" target="_blank" >RIV/00216305:26220/26:0197853 - isvavai.cz</a>

Výsledek na webu

<a href="https://aes2.org/publications/elibrary-page/?id=22953" target="_blank" >https://aes2.org/publications/elibrary-page/?id=22953</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.17743/jaes.2022.0221" target="_blank" >10.17743/jaes.2022.0221</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion

Popis výsledku v původním jazyce

The restoration of nonlinearly distorted audio signals, alongside the identification of the applied memoryless nonlinear operation, is studied. The paper focuses on the difficult but practically important case in which both the nonlinearity and the original input signal are unknown. The proposed method uses a generative diffusion model trained unconditionally on guitar or speech signals to jointly model and invert the nonlinearsystem at inference time. Both the memoryless nonlinear function model and the restored audio signal are obtained as output. Examples of successful blind estimation of hard and soft clipping, digital quantization, half-wave rectification, and wavefolding nonlinearities are presented. Our results suggest that, out of the nonlinear functions tested here, the cubic Catmull-Rom spline is best suited to approximating these nonlinearities. In the case of guitar recordings, comparisons with informed and supervised restoration methods show that the proposed blind method is at least as good as they are in terms of objective metrics. Experiments on distorted speech show that the proposed blind method outperforms general-purpose speech enhancement techniques and restores the original voice quality. The proposed method can be applied to memoryless audio effects modeling, restoration of music and speech recordings, and characterization of analog recording media.

Název v anglickém jazyce

Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion

Popis výsledku anglicky

The restoration of nonlinearly distorted audio signals, alongside the identification of the applied memoryless nonlinear operation, is studied. The paper focuses on the difficult but practically important case in which both the nonlinearity and the original input signal are unknown. The proposed method uses a generative diffusion model trained unconditionally on guitar or speech signals to jointly model and invert the nonlinearsystem at inference time. Both the memoryless nonlinear function model and the restored audio signal are obtained as output. Examples of successful blind estimation of hard and soft clipping, digital quantization, half-wave rectification, and wavefolding nonlinearities are presented. Our results suggest that, out of the nonlinear functions tested here, the cubic Catmull-Rom spline is best suited to approximating these nonlinearities. In the case of guitar recordings, comparisons with informed and supervised restoration methods show that the proposed blind method is at least as good as they are in terms of objective metrics. Experiments on distorted speech show that the proposed blind method outperforms general-purpose speech enhancement techniques and restores the original voice quality. The proposed method can be applied to memoryless audio effects modeling, restoration of music and speech recordings, and characterization of analog recording media.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

<a href="/cs/project/GA23-07294S" target="_blank" >GA23-07294S: Od perceptronu k percepci: psychoakusticky motivovaná rekonstrukce audio signálu s využitím prvků hlubokého učení</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of the Audio Engineering Society

ISSN

1549-4950

e-ISSN

—

Svazek periodika

73

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

519-532

Kód UT WoS článku

001571323900003

EID výsledku v databázi Scopus

—