Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport

11/11/2021
by   Hsin-Yi Lin, et al.
11

This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing. The DOTN aims to estimate clean references of noisy speech in a target domain, by exploiting the knowledge available from the source domain. The domain shift between training and testing data has been reported to be an obstacle to learning problems in diverse fields. Although rich literature exists on unsupervised domain adaptation for classification, the methods proposed, especially in regressions, remain scarce and often depend on additional information regarding the input data. The proposed DOTN approach tactically fuses the optimal transport (OT) theory from mathematical analysis with generative adversarial frameworks, to help evaluate continuous labels in the target domain. The experimental results on two SE tasks demonstrate that by extending the classical OT formulation, our proposed DOTN outperforms previous adversarial domain adaptation frameworks in a purely unsupervised manner.

READ FULL TEXT

page 9

page 16

page 17

page 18

page 19

research
12/03/2021

Hierarchical Optimal Transport for Unsupervised Domain Adaptation

In this paper, we propose a novel approach for unsupervised domain adapt...
research
12/09/2021

Domain Adaptation and Autoencoder Based Unsupervised Speech Enhancement

As a category of transfer learning, domain adaptation plays an important...
research
07/19/2018

Noise Adaptive Speech Enhancement using Domain Adversarial Training

In this study, we propose a novel noise adaptive speech enhancement (SE)...
research
05/24/2017

Joint Distribution Optimal Transportation for Domain Adaptation

This paper deals with the unsupervised domain adaptation problem, where ...
research
05/22/2022

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

Unsupervised domain adaptation is one of the challenging problems in com...
research
08/24/2023

Match-And-Deform: Time Series Domain Adaptation through Optimal Transport and Temporal Alignment

While large volumes of unlabeled data are usually available, associated ...
research
12/24/2020

Unsupervised neural adaptation model based on optimal transport for spoken language identification

Due to the mismatch of statistical distributions of acoustic speech betw...

Please sign up or login with your details

Forgot password? Click here to reset