Low-Delay Analog Joint Source-Channel Coding with Deep Learning

We consider the design of low-delay joint source-channel coding (JSCC) schemes for the transmission of discrete-time analog sources over noisy channels based on deep neural networks. The design problem is addressed as optimization of an autoencoder model, and several scenarios are discussed. For poi...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on communications Ročník 71; číslo 1; s. 1
Hlavní autori: Xuan, Ziwei, Narayanan, Krishna
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:0090-6778, 1558-0857
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract We consider the design of low-delay joint source-channel coding (JSCC) schemes for the transmission of discrete-time analog sources over noisy channels based on deep neural networks. The design problem is addressed as optimization of an autoencoder model, and several scenarios are discussed. For point-to-point communication of independent and identically distributed (i.i.d) Gaussian sources and Gauss-Markov sources over additive-white Gaussian noise (AWGN) channels, the encoder and decoder are constructed using recurrent neural networks (RNNs). With minimum prior knowledge used for design, the performance of these RNNs-based models is optimized using fine tuning techniques during training. Sinusoidal representation networks (SIRENs)-based models are proposed and optimized for three JSCC problems namely, transmitting multivariate Gaussian sources over AWGN channels, transmitting i.i.d Gaussian sources with side information at the decoder, and for communicating correlated sources over orthogonal Gaussian channels. We show that these deep learning-based JSCC schemes perform comparably or better than state-of-the-art (SOTA) traditional schemes. The proposed scheme can extend flexibly to different pairs of source and channel dimensions. Moreover, the spontaneously learned encoder mappings exhibit structured patterns that are interpretable.
AbstractList We consider the design of low-delay joint source-channel coding (JSCC) schemes for the transmission of discrete-time analog sources over noisy channels based on deep neural networks. The design problem is addressed as optimization of an autoencoder model, and several scenarios are discussed. For point-to-point communication of independent and identically distributed (i.i.d) Gaussian sources and Gauss-Markov sources over additive-white Gaussian noise (AWGN) channels, the encoder and decoder are constructed using recurrent neural networks (RNNs). With minimum prior knowledge used for design, the performance of these RNNs-based models is optimized using fine tuning techniques during training. Sinusoidal representation networks (SIRENs)-based models are proposed and optimized for three JSCC problems namely, transmitting multivariate Gaussian sources over AWGN channels, transmitting i.i.d Gaussian sources with side information at the decoder, and for communicating correlated sources over orthogonal Gaussian channels. We show that these deep learning-based JSCC schemes perform comparably or better than state-of-the-art (SOTA) traditional schemes. The proposed scheme can extend flexibly to different pairs of source and channel dimensions. Moreover, the spontaneously learned encoder mappings exhibit structured patterns that are interpretable.
Author Narayanan, Krishna
Xuan, Ziwei
Author_xml – sequence: 1
  givenname: Ziwei
  orcidid: 0000-0002-0279-5260
  surname: Xuan
  fullname: Xuan, Ziwei
  organization: Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
– sequence: 2
  givenname: Krishna
  orcidid: 0000-0001-8742-5332
  surname: Narayanan
  fullname: Narayanan, Krishna
  organization: Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
BookMark eNp9kEtPAjEUhRuDiYj-Ad1M4nrw9jWdrgwZfGYIC3HdlE6BkrHFzhDCv3cQ4sKFq5vcnO_k5LtEPR-8RegGwxBjkPezYjqZDAkQMqSEkFywM9THnOcp5Fz0UB9AQpoJkV-gy6ZZAwADSvvooQy7dGxrvU9GXtdhmbwF59vkPWyjsWmx0t7bOilC5fwy2bl2lYyt3SSl1dF3ryt0vtB1Y69Pd4A-nh5nxUtaTp9fi1GZGiJ5m2qB9QI4XRjGsACbZ1rPmcXaYE4kJVSYucZMMmZkVdGME21NxnTVzQScETpAd8feTQxfW9u0at0t7BY3ioiMY8EFPqTyY8rE0DTRLpRxrW5d8G3UrlYY1EGX-tGlDrrUSVeHkj_oJrpPHff_Q7dHyFlrfwEpOYMM6DehkHYf
CODEN IECMBT
CitedBy_id crossref_primary_10_1109_TCOMM_2024_3407204
crossref_primary_10_1109_TIT_2023_3302318
crossref_primary_10_1111_coin_70021
crossref_primary_10_1109_TIT_2023_3297962
crossref_primary_10_1111_coin_70045
crossref_primary_10_1109_LCOMM_2025_3556673
crossref_primary_10_1109_TCOMM_2024_3406381
crossref_primary_10_4108_eetsis_8678
crossref_primary_10_1186_s13634_024_01132_4
crossref_primary_10_1007_s11276_024_03830_1
crossref_primary_10_1109_TWC_2024_3422794
Cites_doi 10.1109/TIT.2006.878212
10.1109/DCC.2010.92
10.1109/TCOMM.2009.04.070165
10.1109/CISS.2014.6814102
10.1109/TCOMM.2014.011914.130382
10.1109/ISWCS.2009.5285266
10.1109/ALLERTON.2019.8919888
10.1162/neco.1997.9.8.1735
10.1016/S0019-9958(78)90034-7
10.1109/TCOMM.2011.081711.090298
10.1109/26.701312
10.1109/CISS.2012.6310715
10.1109/JSAIT.2020.2987203
10.1007/978-3-7091-2928-9_1
10.1109/SPCOM50965.2020.9179539
10.1109/TIT.2002.1003821
10.1109/IEDM.2018.8614612
10.1109/TCOMM.2015.2494004
10.1109/TCCN.2019.2919300
10.1109/JSAC.2021.3078489
10.23919/EUSIPCO54536.2021.9616186
10.1109/TCOMM.2009.0901.070075
10.1109/SPAWC48557.2020.9154331
10.1109/TIT.1965.1053821
10.1109/ICASSP.2016.7472380
10.1109/DCC.2018.00023
10.1109/TIT.2014.2361532
10.1109/ICASSP.2018.8461983
10.1109/CISS.2015.7086847
10.1109/ICC42927.2021.9500692
10.1525/9780520355408
10.1109/JSAIT.2020.2988577
10.1109/TIT.1956.1056823
10.3390/e15062129
10.1002/0471200611
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
8FD
L7M
DOI 10.1109/TCOMM.2022.3222874
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Technology Research Database
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1558-0857
EndPage 1
ExternalDocumentID 10_1109_TCOMM_2022_3222874
9954060
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: CCF-1718886
  funderid: 10.13039/100000001
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IES
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
ZCA
ZCG
AAYXX
CITATION
7SP
8FD
L7M
ID FETCH-LOGICAL-c295t-a71af053fc44170e86aab4e1ac15293237cba14944c9dd3652aec64ad04001623
IEDL.DBID RIE
ISICitedReferencesCount 21
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000967033700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0090-6778
IngestDate Mon Jun 30 10:21:23 EDT 2025
Sat Nov 29 04:08:25 EST 2025
Tue Nov 18 22:44:19 EST 2025
Wed Aug 27 02:29:15 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c295t-a71af053fc44170e86aab4e1ac15293237cba14944c9dd3652aec64ad04001623
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-0279-5260
0000-0001-8742-5332
PQID 2765175712
PQPubID 85472
PageCount 1
ParticipantIDs ieee_primary_9954060
crossref_citationtrail_10_1109_TCOMM_2022_3222874
crossref_primary_10_1109_TCOMM_2022_3222874
proquest_journals_2765175712
PublicationCentury 2000
PublicationDate 2023-01-01
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-01-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on communications
PublicationTitleAbbrev TCOMM
PublicationYear 2023
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref35
Ramstad (ref3) 2002; 98
ref12
ref34
ref15
ref37
ref14
ref36
ref31
ref30
ref11
ref33
Loshchilov (ref41) 2016
ref10
ref32
Shazeer (ref38) 2017
ref1
ref17
ref39
Chung (ref2) 2000
Alustiza (ref16)
ref19
Sitzmann (ref43) 2020
ref18
Smith (ref40) 2017
Loshchilov (ref42) 2017
Liu (ref7) 2016
ref24
ref23
ref26
ref25
ref20
ref22
ref44
ref21
ref28
ref27
ref29
ref8
ref9
ref4
ref6
Plötz (ref45); 31
ref5
References_xml – ident: ref9
  doi: 10.1109/TIT.2006.878212
– volume: 98
  start-page: 114
  issue: 1
  year: 2002
  ident: ref3
  article-title: Shannon mappings for robust communication
  publication-title: Telektronikk
– ident: ref19
  doi: 10.1109/DCC.2010.92
– ident: ref10
  doi: 10.1109/TCOMM.2009.04.070165
– ident: ref14
  doi: 10.1109/CISS.2014.6814102
– ident: ref12
  doi: 10.1109/TCOMM.2014.011914.130382
– ident: ref17
  doi: 10.1109/ISWCS.2009.5285266
– volume-title: Reliable and Efficient Transmission of Signals: Coding Design, Beamforming Optimization and Multi-Point Cooperation
  year: 2016
  ident: ref7
– ident: ref26
  doi: 10.1109/ALLERTON.2019.8919888
– ident: ref37
  doi: 10.1162/neco.1997.9.8.1735
– ident: ref36
  doi: 10.1016/S0019-9958(78)90034-7
– ident: ref5
  doi: 10.1109/TCOMM.2011.081711.090298
– ident: ref6
  doi: 10.1109/26.701312
– ident: ref18
  doi: 10.1109/CISS.2012.6310715
– ident: ref22
  doi: 10.1109/JSAIT.2020.2987203
– ident: ref34
  doi: 10.1007/978-3-7091-2928-9_1
– ident: ref29
  doi: 10.1109/SPCOM50965.2020.9179539
– year: 2017
  ident: ref38
  article-title: Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
  publication-title: arXiv:1701.06538
– year: 2017
  ident: ref40
  article-title: Don’t decay the learning rate, increase the batch size
  publication-title: arXiv:1711.00489
– ident: ref44
  doi: 10.1109/TIT.2002.1003821
– ident: ref23
  doi: 10.1109/IEDM.2018.8614612
– year: 2017
  ident: ref42
  article-title: Decoupled weight decay regularization
  publication-title: arXiv:1711.05101
– start-page: 1603
  volume-title: Proc. 20th Eur. Signal Process. Conf.
  ident: ref16
  article-title: Bandwidth-reduction analog mappings for AWGN channels with side information
– volume-title: On the construction of some capacity-approaching coding schemes
  year: 2000
  ident: ref2
– year: 2020
  ident: ref43
  article-title: Implicit neural representations with periodic activation functions
  publication-title: arXiv:2006.09661
– ident: ref20
  doi: 10.1109/TCOMM.2015.2494004
– ident: ref21
  doi: 10.1109/TCCN.2019.2919300
– ident: ref28
  doi: 10.1109/JSAC.2021.3078489
– ident: ref31
  doi: 10.23919/EUSIPCO54536.2021.9616186
– ident: ref4
  doi: 10.1109/TCOMM.2009.0901.070075
– volume: 31
  start-page: 1087
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref45
  article-title: Neural nearest neighbors networks
– ident: ref27
  doi: 10.1109/SPAWC48557.2020.9154331
– year: 2016
  ident: ref41
  article-title: SGDR: Stochastic gradient descent with warm restarts
  publication-title: arXiv:1608.03983
– ident: ref1
  doi: 10.1109/TIT.1965.1053821
– ident: ref11
  doi: 10.1109/ICASSP.2016.7472380
– ident: ref24
  doi: 10.1109/DCC.2018.00023
– ident: ref8
  doi: 10.1109/TIT.2014.2361532
– ident: ref25
  doi: 10.1109/ICASSP.2018.8461983
– ident: ref15
  doi: 10.1109/CISS.2015.7086847
– ident: ref30
  doi: 10.1109/ICC42927.2021.9500692
– ident: ref35
  doi: 10.1525/9780520355408
– ident: ref39
  doi: 10.1109/JSAIT.2020.2988577
– ident: ref33
  doi: 10.1109/TIT.1956.1056823
– ident: ref13
  doi: 10.3390/e15062129
– ident: ref32
  doi: 10.1002/0471200611
SSID ssj0004033
Score 2.5037754
Snippet We consider the design of low-delay joint source-channel coding (JSCC) schemes for the transmission of discrete-time analog sources over noisy channels based...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Artificial neural networks
AWGN channels
Channels
Coders
Coding
Communication
Decoding
Deep learning
Design optimization
Distortion
distributed source-channel coding
Joint source-channel coding
Machine learning
Neural networks
Noise measurement
Random noise
Receivers
Recurrent neural networks
RNNs
SIRENs
Training
Transmission
Title Low-Delay Analog Joint Source-Channel Coding with Deep Learning
URI https://ieeexplore.ieee.org/document/9954060
https://www.proquest.com/docview/2765175712
Volume 71
WOSCitedRecordID wos000967033700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1558-0857
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004033
  issn: 0090-6778
  databaseCode: RIE
  dateStart: 19720101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fS8MwED7m8EEf_DXF6ZQ8-Kbd2jRrmieRTRHZpuCEvZUkTcdgtGPrFP97k7SbiiL41ocLhEsvd99d7juAi5AJfTFiqWGJRjpEEs_hkiVOiBOhDTNOOLWNwj06GISjEXuqwNW6F0YpZR-fqab5tLX8OJNLkyprGe4yN9AAfYPSoOjV-uyBdP2ScdI8Z6fhqkHGZa1h57Hf11AQ46apK4SUfHNCdqrKj6vY-pe73f_tbA92yjgS3RQHvw8VlR7A9hd2wRpc97I3p6um_B0Z6pFsjB6ySZqjZ5uvd0xfQaqmqJMZ94VMQhZ1lZqhknJ1fAgvd7fDzr1TzktwJGbt3OHU44k2qkSauWKuCgPOBVEel9pJ6zjNp1JwjYgIkSyO_aCNuZIB4bExZE_HQUdQTbNUHQPyKRNUi1IRa7wYmtoa4Vy6jLeF8pmog7dSYCRLMnEz02IaWVDhssgqPTJKj0ql1-FyvWZWUGn8KV0zal5LlhquQ2N1TlFpbYsI06CtwyDq4ZPfV53ClhkTX6ROGlDN50t1BpvyNZ8s5uf2R_oAR6PCkw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB6KCurBVxXrMwdvunXf2ZxEquJjWwUr9LZks9lSKLtit4r_3kyaVkURvO1hAmGyk5lvJvMNwFHEUnUxukLBEoV0fOE7FhcstyI3T5VhZjmnulE4pp1O1OuxhxqczHphpJT68Zls4qeu5WelGGOq7BS5y-xQAfR5nJxlurU-uyBtz3BO4oN2Gk1bZGx22m3dt9sKDLpuEysLEfW_uSE9V-XHZaw9zNXq__a2BismkiTnk6Nfh5osNmD5C79gHc7i8s26kEP-TpB8pOyT23JQVORRZ-wt7Cwo5JC0SnRgBFOy5ELKZ2JIV_ub8HR12W1dW2ZigiVcFlQWpw7PlVnlAieL2TIKOU996XCh3LSK1DwqUq4wke8LlmVeGLhcitDnGZqyoyKhLZgrykJuA_EoS6kSpWmmEGOE1TWfc2EzHqTSY2kDnKkCE2HoxHGqxTDRsMJmiVZ6gkpPjNIbcDxb8zwh0_hTuo5qnkkaDTdgb3pOibG3UeLSMFCBEHXcnd9XHcLidbcdJ_FN524XlnBo_CSRsgdz1ctY7sOCeK0Go5cD_VN9AJrBxdw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Low-Delay+Analog+Joint+Source-Channel+Coding+With+Deep+Learning&rft.jtitle=IEEE+transactions+on+communications&rft.au=Xuan%2C+Ziwei&rft.au=Narayanan%2C+Krishna&rft.date=2023-01-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=0090-6778&rft.eissn=1558-0857&rft.volume=71&rft.issue=1&rft.spage=40&rft_id=info:doi/10.1109%2FTCOMM.2022.3222874&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon