Report
View in EDS

SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications

Bibliographic Details
Title: SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications
Authors: Mo, Hao, Sun, Yaping, Yao, Shumin, Chen, Hao, Chen, Zhiyong, Xu, Xiaodong, Ma, Nan, Tao, Meixia, Cui, Shuguang
Publication Year: 2025
Collection: Computer Science
Mathematics
Subject Terms: Electrical Engineering and Systems Science - Signal Processing, Computer Science - Information Theory
More Details: Score-based diffusion models represent a significant variant within the diffusion model family and have seen extensive application in the increasingly popular domain of generative tasks. Recent investigations have explored the denoising potential of diffusion models in semantic communications. However, in previous paradigms, noise distortion in the diffusion process does not match precisely with digital channel noise characteristics. In this work, we introduce the Score-Based Channel Denoising Model (SCDM) for Digital Semantic Communications (DSC). SCDM views the distortion of constellation symbol sequences in digital transmission as a score-based forward diffusion process. We design a tailored forward noise corruption to align digital channel noise properties in the training phase. During the inference stage, the well-trained SCDM can effectively denoise received semantic symbols under various SNR conditions, reducing the difficulty for the semantic decoder in extracting semantic information from the received noisy symbols and thereby enhancing the robustness of the reconstructed semantic information. Experimental results show that SCDM outperforms the baseline model in PSNR, SSIM, and MSE metrics, particularly at low SNR levels. Moreover, SCDM reduces storage requirements by a factor of 7.8. This efficiency in storage, combined with its robust denoising capability, makes SCDM a practical solution for DSC across diverse channel conditions.
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2501.17876
Accession Number: edsarx.2501.17876
Database: arXiv
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://arxiv.org/abs/2501.17876
    Name: EDS - Arxiv
    Category: fullText
    Text: View this record from Arxiv
    MouseOverText: View this record from Arxiv
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20250118&spage=&pages=&title=SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications&atitle=SCDM%3A%20Score-Based%20Channel%20Denoising%20Model%20for%20Digital%20Semantic%20Communications&aulast=Mo%2C%20Hao&id=DOI:
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
Header DbId: edsarx
DbLabel: arXiv
An: edsarx.2501.17876
RelevancyScore: 1129
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 1129.22924804688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mo%2C+Hao%22">Mo, Hao</searchLink><br /><searchLink fieldCode="AR" term="%22Sun%2C+Yaping%22">Sun, Yaping</searchLink><br /><searchLink fieldCode="AR" term="%22Yao%2C+Shumin%22">Yao, Shumin</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Hao%22">Chen, Hao</searchLink><br /><searchLink fieldCode="AR" term="%22Chen%2C+Zhiyong%22">Chen, Zhiyong</searchLink><br /><searchLink fieldCode="AR" term="%22Xu%2C+Xiaodong%22">Xu, Xiaodong</searchLink><br /><searchLink fieldCode="AR" term="%22Ma%2C+Nan%22">Ma, Nan</searchLink><br /><searchLink fieldCode="AR" term="%22Tao%2C+Meixia%22">Tao, Meixia</searchLink><br /><searchLink fieldCode="AR" term="%22Cui%2C+Shuguang%22">Cui, Shuguang</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Computer Science<br />Mathematics
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Signal+Processing%22">Electrical Engineering and Systems Science - Signal Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Information+Theory%22">Computer Science - Information Theory</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Score-based diffusion models represent a significant variant within the diffusion model family and have seen extensive application in the increasingly popular domain of generative tasks. Recent investigations have explored the denoising potential of diffusion models in semantic communications. However, in previous paradigms, noise distortion in the diffusion process does not match precisely with digital channel noise characteristics. In this work, we introduce the Score-Based Channel Denoising Model (SCDM) for Digital Semantic Communications (DSC). SCDM views the distortion of constellation symbol sequences in digital transmission as a score-based forward diffusion process. We design a tailored forward noise corruption to align digital channel noise properties in the training phase. During the inference stage, the well-trained SCDM can effectively denoise received semantic symbols under various SNR conditions, reducing the difficulty for the semantic decoder in extracting semantic information from the received noisy symbols and thereby enhancing the robustness of the reconstructed semantic information. Experimental results show that SCDM outperforms the baseline model in PSNR, SSIM, and MSE metrics, particularly at low SNR levels. Moreover, SCDM reduces storage requirements by a factor of 7.8. This efficiency in storage, combined with its robust denoising capability, makes SCDM a practical solution for DSC across diverse channel conditions.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Working Paper
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2501.17876" linkWindow="_blank">http://arxiv.org/abs/2501.17876</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsarx.2501.17876
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2501.17876
RecordInfo BibRecord:
  BibEntity:
    Subjects:
      – SubjectFull: Electrical Engineering and Systems Science - Signal Processing
        Type: general
      – SubjectFull: Computer Science - Information Theory
        Type: general
    Titles:
      – TitleFull: SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mo, Hao
      – PersonEntity:
          Name:
            NameFull: Sun, Yaping
      – PersonEntity:
          Name:
            NameFull: Yao, Shumin
      – PersonEntity:
          Name:
            NameFull: Chen, Hao
      – PersonEntity:
          Name:
            NameFull: Chen, Zhiyong
      – PersonEntity:
          Name:
            NameFull: Xu, Xiaodong
      – PersonEntity:
          Name:
            NameFull: Ma, Nan
      – PersonEntity:
          Name:
            NameFull: Tao, Meixia
      – PersonEntity:
          Name:
            NameFull: Cui, Shuguang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 18
              M: 01
              Type: published
              Y: 2025
ResultId 1