{"id":"https://openalex.org/W4406089864","doi":"https://doi.org/10.1109/jstsp.2024.3521277","title":"Low-Latency Deep Analog Speech Transmission Using Joint Source Channel Coding","display_name":"Low-Latency Deep Analog Speech Transmission Using Joint Source Channel Coding","publication_year":2024,"publication_date":"2024-12-01","ids":{"openalex":"https://openalex.org/W4406089864","doi":"https://doi.org/10.1109/jstsp.2024.3521277"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2024.3521277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3521277","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115779868","display_name":"Mohammad Bokaei","orcid":"https://orcid.org/0009-0006-7455-9853"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mohammad Bokaei","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0009-0006-7455-9853","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I4210130492","display_name":"Oticon Medical (Denmark)","ror":"https://ror.org/03c5ds320","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210130492"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Oticon A/S, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-1478-622X","affiliations":[{"raw_affiliation_string":"Oticon A/S, Copenhagen, Denmark","institution_ids":["https://openalex.org/I4210130492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics, Oldenburg University, Oldenburg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3392-2381","affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, Oldenburg University, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023894109","display_name":"Jan \u00d8stergaard","orcid":"https://orcid.org/0000-0002-3724-6114"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jan \u00d8stergaard","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-3724-6114","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8446,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73906544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"18","issue":"8","first_page":"1401","last_page":"1413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8161616325378418},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5769326090812683},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4863305687904358},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4713938534259796},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4354982376098633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3945000469684601},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3554645776748657},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22556647658348083},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15108847618103027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161616325378418},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5769326090812683},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4863305687904358},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4713938534259796},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4354982376098633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3945000469684601},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3554645776748657},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22556647658348083},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15108847618103027},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2024.3521277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2024.3521277","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/5a9c6ce8-ddba-46de-b726-a78d50459785","is_oa":false,"landing_page_url":"https://vbn.aau.dk/da/publications/5a9c6ce8-ddba-46de-b726-a78d50459785","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bokaei, M, Jensen, J, Doclo, S & \u00d8stergaard, J 2024, 'Low-Latency Deep Analog Speech Transmission Using Joint Source Channel Coding', IEEE Journal of Selected Topics in Signal Processing, vol. 18, no. 8, 10824931, pp. 1401-1413. https://doi.org/10.1109/JSTSP.2024.3521277","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1952406298","https://openalex.org/W1988330123","https://openalex.org/W1997834106","https://openalex.org/W2079985975","https://openalex.org/W2098691264","https://openalex.org/W2099547538","https://openalex.org/W2128765501","https://openalex.org/W2140326550","https://openalex.org/W2148164553","https://openalex.org/W2148371116","https://openalex.org/W2148575324","https://openalex.org/W2516001803","https://openalex.org/W2552465432","https://openalex.org/W2760103357","https://openalex.org/W2791686384","https://openalex.org/W2798333393","https://openalex.org/W2919115771","https://openalex.org/W2946889564","https://openalex.org/W2955338161","https://openalex.org/W2963174256","https://openalex.org/W2972359262","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3095095816","https://openalex.org/W3107617916","https://openalex.org/W3120761289","https://openalex.org/W3163082404","https://openalex.org/W3163243746","https://openalex.org/W3166791908","https://openalex.org/W3177376120","https://openalex.org/W3207494168","https://openalex.org/W3214462705","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4231109964","https://openalex.org/W4256264271","https://openalex.org/W4307323391","https://openalex.org/W4388118365","https://openalex.org/W4400277707","https://openalex.org/W4401609485","https://openalex.org/W6631190155","https://openalex.org/W6767111847"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W3203142394","https://openalex.org/W2351061015","https://openalex.org/W2384362569","https://openalex.org/W4220731478","https://openalex.org/W1974101135","https://openalex.org/W2017509870"],"abstract_inverted_index":{"Low-latency":[0],"configurable":[1,46,92],"speech":[2,55,95,109,148],"transmission":[3],"presents":[4],"significant":[5],"challenges":[6],"in":[7,39,145,153,163],"modern":[8],"communication":[9],"systems.":[10,130,178],"Traditional":[11],"methods":[12],"rely":[13],"on":[14,77,106],"separate":[15,31,141],"source":[16],"and":[17,86,150,155,171],"channel":[18,68,157,173],"coding,":[19],"which":[20],"often":[21],"degrades":[22],"performance":[23],"under":[24],"low-latency":[25,47,154],"constraints.":[26],"Moreover,":[27],"non-configurable":[28],"systems":[29,144],"require":[30],"training":[32],"for":[33,54,62],"each":[34],"condition,":[35],"limiting":[36],"their":[37],"adaptability":[38],"resource-constrained":[40],"scenarios.":[41],"This":[42],"paper":[43],"proposes":[44],"a":[45,91,112,119],"deep":[48,78],"Joint":[49],"Source-Channel":[50],"Coding":[51],"(JSCC)":[52],"system":[53,58,101,138],"transmission.":[56],"The":[57,100,131],"can":[59],"be":[60],"configured":[61,165],"varying":[63],"signal-to-noise":[64],"ratios":[65],"(SNR),":[66],"wireless":[67],"conditions,":[69],"or":[70],"bandwidths.":[71],"A":[72],"joint":[73],"source-channel":[74,142],"encoder":[75],"based":[76,105],"neural":[79],"networks":[80],"(DNN)":[81],"is":[82,103],"used":[83],"to":[84],"compress":[85],"transmit":[87],"analog-coded":[88],"information,":[89],"while":[90],"decoder":[93],"reconstructs":[94],"from":[96],"noisy":[97,156],"compressed":[98],"signals.":[99],"latency":[102,114,169],"adaptable":[104],"the":[107,136],"input":[108],"length,":[110],"achieving":[111],"minimum":[113],"of":[115,122,147],"2":[116],"ms,":[117],"with":[118],"lightweight":[120],"architecture":[121],"25":[123],"k":[124],"parameters,":[125],"significantly":[126],"fewer":[127],"than":[128],"state-of-the-art":[129],"simulation":[132],"results":[133],"demonstrate":[134],"that":[135],"proposed":[137],"outperforms":[139],"conventional":[140],"coding":[143,177],"terms":[146],"quality":[149],"intelligibility,":[151],"particularly":[152],"conditions.":[158],"It":[159],"also":[160],"shows":[161],"robustness":[162],"fixed":[164],"scenarios,":[166],"though":[167],"higher":[168],"conditions":[170],"better":[172],"environments":[174],"favor":[175],"traditional":[176]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}