{"id":"https://openalex.org/W4413179627","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11101684","title":"Generative Semantic Communication for Text-to-Speech Synthesis","display_name":"Generative Semantic Communication for Text-to-Speech Synthesis","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4413179627","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11101684"},"language":"en","primary_location":{"id":"doi:10.1109/gcwkshp64532.2024.11101684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11101684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","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/A5103108979","display_name":"Jiahao Zheng","orcid":"https://orcid.org/0000-0001-5169-3183"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahao Zheng","raw_affiliation_strings":["Shenzhen Future Network of Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Future Network of Intelligence Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036242436","display_name":"Jinke Ren","orcid":"https://orcid.org/0000-0002-7409-6127"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinke Ren","raw_affiliation_strings":["Shenzhen Future Network of Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Future Network of Intelligence Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061607503","display_name":"Peng Xu","orcid":"https://orcid.org/0000-0001-7393-2579"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Xu","raw_affiliation_strings":["Shenzhen Future Network of Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Future Network of Intelligence Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832227","display_name":"Zhihao Yuan","orcid":"https://orcid.org/0000-0003-3100-1252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhihao Yuan","raw_affiliation_strings":["Shenzhen Future Network of Intelligence Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Future Network of Intelligence Institute","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100335031","display_name":"Jie Xu","orcid":"https://orcid.org/0009-0006-8697-9273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["School of Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101686970","display_name":"Fangxin Wang","orcid":"https://orcid.org/0000-0003-2559-045X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangxin Wang","raw_affiliation_strings":["School of Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032658108","display_name":"Gui Gui","orcid":"https://orcid.org/0000-0001-7764-1533"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gui Gui","raw_affiliation_strings":["Central South University,School of Automation,Changsha,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,School of Automation,Changsha,China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009164482","display_name":"Shuguang Cui","orcid":"https://orcid.org/0000-0003-2608-775X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuguang Cui","raw_affiliation_strings":["School of Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3556,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63970933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"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":0.8090413808822632},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6423720121383667},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5758172273635864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4821628928184509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46863436698913574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090413808822632},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6423720121383667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5758172273635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4821628928184509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46863436698913574}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcwkshp64532.2024.11101684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11101684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2946889564","https://openalex.org/W2972359262","https://openalex.org/W3202895480","https://openalex.org/W3209984917","https://openalex.org/W4285742007","https://openalex.org/W4307323391","https://openalex.org/W4313350220","https://openalex.org/W4315629832","https://openalex.org/W4319302797","https://openalex.org/W4365420366","https://openalex.org/W4366460484","https://openalex.org/W4394804945","https://openalex.org/W4400277805","https://openalex.org/W4401387161","https://openalex.org/W4401539146","https://openalex.org/W6795261426","https://openalex.org/W6805710207","https://openalex.org/W6851724922"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2380075625","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Semantic":[0],"communication":[1,8,23,56,132],"is":[2],"a":[3,52,69,117,121],"promising":[4],"technology":[5],"to":[6,82,124],"improve":[7],"efficiency":[9],"by":[10],"transmitting":[11],"only":[12],"the":[13,17,77,90,98,105,108,146],"semantic":[14,22,55,85,102,127],"information":[15],"of":[16],"source":[18],"data.":[19],"However,":[20],"traditional":[21],"methods":[24],"primarily":[25],"focus":[26],"on":[27],"data":[28],"reconstruction":[29],"tasks,":[30],"which":[31],"may":[32],"not":[33],"be":[34],"efficient":[35,126],"for":[36,58,145],"emerging":[37],"generative":[38,54,62],"tasks":[39],"such":[40],"as":[41],"text-to-speech":[42],"(TTS)":[43],"synthesis.":[44,113],"To":[45],"address":[46],"this":[47,49],"limitation,":[48],"paper":[50],"develops":[51],"novel":[53],"framework":[57,140],"TTS":[59],"synthesis,":[60],"leveraging":[61],"artificial":[63],"intelligence":[64],"technologies.":[65],"Firstly,":[66],"we":[67,115],"utilize":[68],"pre-trained":[70],"large":[71],"speech":[72,112,148],"model":[73,123],"called":[74],"WavLM":[75],"and":[76,92,120,161],"residual":[78],"vector":[79],"quantization":[80],"method":[81],"construct":[83],"two":[84],"knowledge":[86],"bases":[87],"(KBs)":[88],"at":[89,97,107],"transmitter":[91,99],"receiver,":[93],"respectively.":[94],"The":[95],"KB":[96,106],"enables":[100],"effective":[101],"extraction,":[103],"while":[104],"receiver":[109],"facilitates":[110],"lifelike":[111],"Then,":[114],"employ":[116],"transformer":[118],"encoder":[119],"diffusion":[122],"achieve":[125],"coding":[128],"without":[129],"introducing":[130],"significant":[131],"overhead.":[133],"Finally,":[134],"numerical":[135],"results":[136],"demonstrate":[137],"that":[138],"our":[139],"achieves":[141],"much":[142],"higher":[143],"fidelity":[144],"generated":[147],"than":[149],"four":[150],"baselines,":[151],"in":[152],"both":[153],"cases":[154],"with":[155],"additive":[156],"white":[157],"Gaussian":[158],"noise":[159],"channel":[160],"Rayleigh":[162],"fading":[163],"channel.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}