Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/27913
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Huang, K | - |
dc.contributor.author | Shi, C | - |
dc.contributor.author | Gan, L | - |
dc.contributor.author | Liu, H | - |
dc.coverage.spatial | Seoul, South Korea | - |
dc.date.accessioned | 2023-12-21T18:50:32Z | - |
dc.date.available | 2023-12-21T18:50:32Z | - |
dc.date.issued | 2024-03-18 | - |
dc.identifier | ORCiD: Lu Gan https://orcid.org/0000-0003-1056-7660 | - |
dc.identifier.citation | Huang, K. et al. (2024) 'Understanding Gaussian Noise Mismatch: A Hellinger Distance Approach', ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, South Korea, 15-19 April, pp. 9051 - 9055. doi: 10.1109/ICASSP48485.2024.10446269. | en_US |
dc.identifier.issn | 1520-6149 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/27913 | - |
dc.description.abstract | This paper explores noise-mismatched models using the Hellinger distance. In many applications, the design/training stage often assumes an independent and identically distributed (i.i.d.) Gaussian prior noise, but the real world introduces Gaussian noise with arbitrary covariance, creating a mismatch. We analyze the impact on system output and study optimal injected noise intensity for training/design. While theory assumes Gaussian sources, it provides guidance for non-Gaussian settings too. Experiments with Cycle-GAN for image-to-image translation validate the theory, producing results consistenting with derivations. Overall, this work provides theoretical and empirical insights into designing systems robust to noise uncertainties beyond simplified assumptions. | - |
dc.format.extent | 9051 - 9055 | - |
dc.format.medium | Print-Electronic | - |
dc.language.iso | en_US | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.rights | Copyright © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works (see: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/). | - |
dc.rights.uri | https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/ | - |
dc.source | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing | - |
dc.source | 2024 IEEE International Conference on Acoustics, Speech and Signal Processing | - |
dc.subject | noise mismatch | en_US |
dc.subject | Hellinger distance | en_US |
dc.subject | fdivergence | en_US |
dc.subject | unpaired image-to-image translation | en_US |
dc.title | Understanding Gaussian Noise Mismatch: A Hellinger Distance Approach | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.doi | https://doi.org/10.1109/ICASSP48485.2024.10446269 | - |
pubs.finish-date | 2024-04-19 | - |
pubs.finish-date | 2024-04-19 | - |
pubs.publication-status | Published | - |
pubs.start-date | 2024-04-14 | - |
pubs.start-date | 2024-04-14 | - |
dc.identifier.eissn | 2379-190X | - |
dc.rights.holder | Institute of Electrical and Electronics Engineers (IEEE) | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © 2024 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works by sending a request to pubs-permissions@ieee.org. See https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/ for more information. | 5.53 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.