{"id":"https://openalex.org/W4393140342","doi":"https://doi.org/10.1109/jiot.2024.3378779","title":"A Perceptually Motivated Approach for Low-Complexity Speech Semantic Communication","display_name":"A Perceptually Motivated Approach for Low-Complexity Speech Semantic Communication","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4393140342","doi":"https://doi.org/10.1109/jiot.2024.3378779"},"language":"en","primary_location":{"id":"doi:10.1109/jiot.2024.3378779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3378779","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5103093817","display_name":"Xiaojiao Chen","orcid":"https://orcid.org/0000-0002-5458-7025"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojiao Chen","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5458-7025","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378497","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0002-3653-9951"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Wang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3653-9951","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040488464","display_name":"Liang Xu","orcid":"https://orcid.org/0000-0002-4952-7300"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xu","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057472782","display_name":"Jingxuan Huang","orcid":"https://orcid.org/0000-0002-7356-2907"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingxuan Huang","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7356-2907","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005456828","display_name":"Zesong Fei","orcid":"https://orcid.org/0000-0002-7576-625X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zesong Fei","raw_affiliation_strings":["School of Information and Electronics, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7576-625X","affiliations":[{"raw_affiliation_string":"School of Information and Electronics, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103093817"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":4.2746,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9490537,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":"12","first_page":"22054","last_page":"22065"},"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8774101734161377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5455346703529358},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.5386291742324829},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4708546996116638},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3963962495326996},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3518034815788269},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13537836074829102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8774101734161377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5455346703529358},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.5386291742324829},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4708546996116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3963962495326996},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3518034815788269},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13537836074829102}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2024.3378779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2024.3378779","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8482837622","display_name":null,"funder_award_id":"62201044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1989351718","https://openalex.org/W2042563853","https://openalex.org/W2141998673","https://openalex.org/W2190237714","https://openalex.org/W2666368276","https://openalex.org/W2768814045","https://openalex.org/W2779699222","https://openalex.org/W2890964092","https://openalex.org/W2963174256","https://openalex.org/W2970006822","https://openalex.org/W2978725006","https://openalex.org/W3082224546","https://openalex.org/W3094502228","https://openalex.org/W3098418424","https://openalex.org/W3112702554","https://openalex.org/W3144035034","https://openalex.org/W3166791908","https://openalex.org/W3215615641","https://openalex.org/W4210624746","https://openalex.org/W4226150551","https://openalex.org/W4253671238","https://openalex.org/W4283021596","https://openalex.org/W4309400187","https://openalex.org/W4312349930","https://openalex.org/W4313350178","https://openalex.org/W4313350185","https://openalex.org/W4315629708","https://openalex.org/W4319302797","https://openalex.org/W4372348936","https://openalex.org/W4375869212","https://openalex.org/W4385819970","https://openalex.org/W4386883058","https://openalex.org/W4387885896","https://openalex.org/W4390874575","https://openalex.org/W6631190155","https://openalex.org/W6810966997"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Deep":[0],"learning-based":[1],"semantic":[2,21,37,44,61,85,97,126,134,141,203,232],"communication":[3,7,22,45,62,86,98,105,233],"is":[4,219],"an":[5,103],"emerging":[6],"method":[8,186,234],"that":[9,43,169,183],"achieves":[10],"cooperative":[11],"transmission":[12,30,50,146,197,204,209,218],"between":[13],"source":[14,110],"and":[15,31,73,112,144,167,191,211,239],"channel.":[16],"The":[17],"primary":[18],"objectives":[19],"of":[20,28,36,76,84,125,140,151,214,227],"are":[23],"to":[24,65,107,162,243],"enhance":[25,163],"the":[26,33,71,74,77,81,109,114,118,122,138,149,164,170,175,184,208,212,225,230],"efficiency":[27],"information":[29,142],"ensure":[32,121],"accurate":[34,123],"restoration":[35],"content.":[38],"Recent":[39],"studies":[40],"have":[41],"shown":[42],"performs":[46,187],"well":[47],"in":[48,53],"enhancing":[49],"rates,":[51],"especially":[52],"low":[54],"signal-to-noise":[55],"ratio":[56],"environments.":[57],"However,":[58],"existing":[59,195,201],"speech":[60,68,96,111,116,172,196],"methods":[63],"neglect":[64],"account":[66],"for":[67,217],"perception":[69],"at":[70,117],"receiver":[72],"complexity":[75,238],"method,":[78],"which":[79,136],"limits":[80],"practical":[82],"implementation":[83],"methods.":[87,198],"In":[88],"this":[89],"paper,":[90],"we":[91,101,128,206],"propose":[92],"a":[93,130,154,236],"perceptually-motivated,":[94],"low-complexity":[95,131],"method.":[99],"Specifically,":[100],"employ":[102],"end-to-end":[104],"approach":[106],"transmit":[108],"obtain":[113],"reconstructed":[115,171],"receiver.":[119],"To":[120],"extraction":[124,143],"information,":[127],"present":[129],"fully":[132],"convolutional":[133],"encoder,":[135],"increases":[137],"accuracy":[139],"improves":[145],"efficiency.":[147],"Considering":[148],"sensitivity":[150],"human":[152,176],"perception,":[153],"multi-resolution":[155],"joint":[156],"loss":[157],"function":[158],"has":[159,235],"been":[160],"implemented":[161],"model\u2019s":[165],"performance":[166],"guarantee":[168],"aligns":[173],"with":[174,200],"ear\u2019s":[177],"auditory":[178],"perception.":[179],"Experimental":[180],"results":[181],"show":[182],"proposed":[185,231],"better":[188],"on":[189],"objective":[190],"subjective":[192],"metrics":[193],"than":[194],"Compared":[199],"neural":[202],"methods,":[205],"improve":[207],"efficiency,":[210],"number":[213],"symbols":[215],"needed":[216],"decreased":[220],"by":[221],"60%":[222],"without":[223],"compromising":[224],"quality":[226],"speech.":[228],"Furthermore,":[229],"lower":[237],"consumes":[240],"less":[241],"time":[242],"transmit.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}