{"id":"https://openalex.org/W4392903433","doi":"https://doi.org/10.1109/icassp48485.2024.10447612","title":"Diffusion Models for Audio Semantic Communication","display_name":"Diffusion Models for Audio Semantic Communication","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903433","doi":"https://doi.org/10.1109/icassp48485.2024.10447612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003606065","display_name":"Eleonora Grassucci","orcid":"https://orcid.org/0000-0003-4626-4506"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Eleonora Grassucci","raw_affiliation_strings":["Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106469480","display_name":"C. Marinoni","orcid":"https://orcid.org/0009-0003-3716-7103"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Christian Marinoni","raw_affiliation_strings":["Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andrea Rodriguez","orcid":null},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Rodriguez","raw_affiliation_strings":["Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019647783","display_name":"Danilo Comminiello","orcid":"https://orcid.org/0000-0003-4067-4504"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danilo Comminiello","raw_affiliation_strings":["Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy","institution_ids":["https://openalex.org/I861853513"]},{"raw_affiliation_string":"Dept. of Information Eng., Electronics and Telecom., Sapienza University of Rome, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":15.2672,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.99478474,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13136","last_page":"13140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9979000091552734,"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":0.8368604183197021},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5040296912193298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4985020160675049},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.49330392479896545},{"id":"https://openalex.org/keywords/transmitter","display_name":"Transmitter","score":0.48418334126472473},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.46041280031204224},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.43036922812461853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3657292127609253},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3511424660682678},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3267263174057007},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.28307539224624634},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.20535361766815186},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1247306764125824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8368604183197021},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5040296912193298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4985020160675049},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.49330392479896545},{"id":"https://openalex.org/C47798520","wikidata":"https://www.wikidata.org/wiki/Q190157","display_name":"Transmitter","level":3,"score":0.48418334126472473},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46041280031204224},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.43036922812461853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3657292127609253},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3511424660682678},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3267263174057007},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28307539224624634},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.20535361766815186},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1247306764125824}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1741589","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1741589","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5356239126","display_name":null,"funder_award_id":"CN00000013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7205771190","display_name":null,"funder_award_id":"PE00000001","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2808122338","https://openalex.org/W2972478942","https://openalex.org/W3105109286","https://openalex.org/W3147966746","https://openalex.org/W3189491540","https://openalex.org/W4290713755","https://openalex.org/W4307079201","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4313350185","https://openalex.org/W4318752004","https://openalex.org/W4372260310","https://openalex.org/W4372265740","https://openalex.org/W4372341905","https://openalex.org/W4375869212","https://openalex.org/W4377086529","https://openalex.org/W4379933627","https://openalex.org/W4380434618","https://openalex.org/W4382240002","https://openalex.org/W4387969125","https://openalex.org/W4388937122","https://openalex.org/W4393058982","https://openalex.org/W6847076894","https://openalex.org/W6847118160","https://openalex.org/W6849109464","https://openalex.org/W6853140940","https://openalex.org/W6856292475"],"related_works":["https://openalex.org/W2355663289","https://openalex.org/W2982399888","https://openalex.org/W2106913410","https://openalex.org/W4380372336","https://openalex.org/W2354248671","https://openalex.org/W2359134391","https://openalex.org/W2594116857","https://openalex.org/W2947628004","https://openalex.org/W2935229758","https://openalex.org/W2502435347"],"abstract_inverted_index":{"Directly":[0],"sending":[1],"audio":[2,64,90],"signals":[3],"from":[4,135],"a":[5,8,11,62,106,164],"transmitter":[6],"to":[7,21,25,39,80,97,116,176,178],"receiver":[9,51],"across":[10],"noisy":[12,154],"channel":[13,170],"may":[14],"absorb":[15],"consistent":[16,47],"bandwidth":[17],"and":[18,43,92,145,167,180,183],"be":[19],"prone":[20],"errors":[22],"when":[23],"trying":[24],"recover":[26],"the":[27,31,33,41,50,55,70,89,94,98,102,113,117,125,128,132,139,150,153,173],"transmitted":[28],"bits.":[29],"On":[30],"contrary,":[32],"recent":[34],"semantic":[35,65],"communication":[36,66,71],"approach":[37],"proposes":[38],"send":[40],"semantics":[42,96],"then":[44],"regenerate":[45],"semantically":[46],"content":[48],"at":[49,121,138],"without":[52],"exactly":[53],"recovering":[54],"bitstream.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"generative":[63],"framework":[67,160],"that":[68,158],"faces":[69],"problem":[72],"as":[73],"an":[74],"inverse":[75],"problem,":[76],"therefore":[77],"being":[78],"robust":[79],"different":[81,169],"corruptions.":[82],"Our":[83],"method":[84],"transmits":[85],"lower-dimensional":[86],"representations":[87],"of":[88,93],"signal":[91,104],"associated":[95],"receiver,":[99],"which":[100],"generates":[101],"corresponding":[103],"with":[105,168],"particular":[107],"focus":[108],"on":[109],"its":[110,122],"meaning":[111],"(i.e.,":[112],"semantics)":[114],"thanks":[115],"conditional":[118],"diffusion":[119,129],"model":[120,130],"core.":[123],"During":[124],"generation":[126],"process,":[127],"restores":[131],"received":[133],"information":[134],"multiple":[136],"degradations":[137],"same":[140],"time":[141],"including":[142],"corruption":[143],"noise":[144],"missing":[146],"parts":[147],"caused":[148],"by":[149],"transmission":[151],"over":[152],"channel.":[155],"We":[156],"show":[157],"our":[159],"outperforms":[161],"competitors":[162],"in":[163],"real-world":[165],"scenario":[166],"conditions.":[171],"Visit":[172],"project":[174],"page":[175],"listen":[177],"samples":[179],"access":[181],"code":[182],"experimental":[184],"procedures:":[185],"https://ispamm.github.io/diffusion-audio-semantic-communication/.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}
