{"id":"https://openalex.org/W4401609485","doi":"https://doi.org/10.1109/icasspw62465.2024.10626232","title":"Deep Low-Latency Joint Speech Transmission and Enhancement over A Gaussian Channel","display_name":"Deep Low-Latency Joint Speech Transmission and Enhancement over A Gaussian Channel","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401609485","doi":"https://doi.org/10.1109/icasspw62465.2024.10626232"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626232","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.19375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058793375","display_name":"Mohammad Hadi Bokaei","orcid":"https://orcid.org/0000-0002-9602-946X"},"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":["Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/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":"Jesper Jensen","raw_affiliation_strings":["Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"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":["University of Oldenburg,Dept. of Medical Physics and Acoustics,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oldenburg,Dept. of Medical Physics and Acoustics,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":["Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"525","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7103789448738098},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6525074243545532},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.5312126874923706},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5255657434463501},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49964118003845215},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4508679211139679},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4400617480278015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4195058345794678},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.2797085642814636},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2725147604942322},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11649855971336365},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10654345154762268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103789448738098},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6525074243545532},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.5312126874923706},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5255657434463501},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49964118003845215},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4508679211139679},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4400617480278015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4195058345794678},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.2797085642814636},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2725147604942322},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11649855971336365},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10654345154762268},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626232","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/4061eddd-93d9-499c-a186-7e3bc5061fdb","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/4061eddd-93d9-499c-a186-7e3bc5061fdb","pdf_url":"https://arxiv.org/pdf/2404.19375","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/4061eddd-93d9-499c-a186-7e3bc5061fdb","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/4061eddd-93d9-499c-a186-7e3bc5061fdb","pdf_url":"https://arxiv.org/pdf/2404.19375","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G7537482475","display_name":"Service-Oriented Ubiquitous Network-Driven Sound","funder_award_id":"956369","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401609485.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2079985975","https://openalex.org/W2516001803","https://openalex.org/W2736068844","https://openalex.org/W2798333393","https://openalex.org/W2946889564","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963408536","https://openalex.org/W2970006822","https://openalex.org/W2971417062","https://openalex.org/W2972359262","https://openalex.org/W2972541922","https://openalex.org/W3027008958","https://openalex.org/W3092028330","https://openalex.org/W3095095816","https://openalex.org/W3099330747","https://openalex.org/W3160576174","https://openalex.org/W3163243746","https://openalex.org/W3166791908","https://openalex.org/W3215615641","https://openalex.org/W4225287045","https://openalex.org/W4245919820","https://openalex.org/W4307323391","https://openalex.org/W4372271367","https://openalex.org/W4388118365","https://openalex.org/W6631190155","https://openalex.org/W6767111847","https://openalex.org/W6777776875","https://openalex.org/W6783867762","https://openalex.org/W6846857581"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463"],"abstract_inverted_index":{"Ensuring":[0],"intelligible":[1],"speech":[2,17,32,50],"communication":[3],"for":[4,29,48],"hearing":[5,95],"assistive":[6,96],"devices":[7],"in":[8,14,68,91,144],"low-latency":[9,30,49,53,61],"scenarios":[10],"presents":[11],"significant":[12],"challenges":[13],"terms":[15],"of":[16,77,104],"enhancement,":[18,35],"coding":[19],"and":[20,34,52,63,134,153],"transmission.":[21],"In":[22],"this":[23,81],"paper,":[24],"we":[25],"propose":[26],"novel":[27],"solutions":[28],"joint":[31,55,132],"transmission":[33,135],"leveraging":[36],"deep":[37],"neural":[38],"networks":[39],"(DNNs).":[40],"Our":[41],"approach":[42],"integrates":[43],"two":[44],"state-of-the-art":[45],"DNN":[46],"architectures":[47],"enhancement":[51,79,133],"analog":[54],"source-channel-based":[56],"transmission,":[57],"creating":[58],"a":[59,131,140],"combined":[60],"system":[62,100,136,143],"jointly":[64],"training":[65],"both":[66],"systems":[67],"an":[69],"end-to-end":[70],"approach.":[71],"Due":[72],"to":[73,122,139],"the":[74,78,92,102],"computational":[75,87],"demands":[76],"system,":[80],"order":[82],"is":[83,89,119,137],"suitable":[84],"when":[85],"high":[86,108],"power":[88],"unavailable":[90],"decoder,":[93],"like":[94],"devices.":[97],"The":[98,124],"proposed":[99],"enables":[101],"configuration":[103],"total":[105],"latency,":[106],"achieving":[107],"performance":[109],"even":[110],"at":[111],"latencies":[112],"as":[113,115],"low":[114],"3":[116],"ms,":[117],"which":[118],"typically":[120],"challenging":[121],"attain.":[123],"simulation":[125],"results":[126],"provide":[127],"compelling":[128],"evidence":[129],"that":[130],"superior":[138],"simple":[141],"concatenation":[142],"diverse":[145],"settings,":[146],"encompassing":[147],"various":[148],"wireless":[149],"channel":[150],"conditions,":[151],"latencies,":[152],"background":[154],"noise":[155],"scenarios.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}
