{"id":"https://openalex.org/W4376480704","doi":"https://doi.org/10.1109/wcnc55385.2023.10118921","title":"Variational Speech Waveform Compression to Catalyze Semantic Communications","display_name":"Variational Speech Waveform Compression to Catalyze Semantic Communications","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4376480704","doi":"https://doi.org/10.1109/wcnc55385.2023.10118921"},"language":"en","primary_location":{"id":"doi:10.1109/wcnc55385.2023.10118921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc55385.2023.10118921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-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/A5001392563","display_name":"Shengshi Yao","orcid":"https://orcid.org/0000-0001-5463-8614"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shengshi Yao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867809","display_name":"Zixuan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Xiao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014392382","display_name":"Sixian Wang","orcid":"https://orcid.org/0000-0002-0621-1285"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sixian Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069582226","display_name":"Jincheng Dai","orcid":"https://orcid.org/0000-0002-0310-568X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincheng Dai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008455605","display_name":"Kai Niu","orcid":"https://orcid.org/0000-0002-8076-1867"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Niu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Peng Cheng Laboratory, Shenzhen, China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100405787","display_name":"Ping Zhang","orcid":"https://orcid.org/0000-0002-0269-104X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China","Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001392563"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78832071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"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/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"}},"topics":[{"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9969000220298767,"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":0.9965000152587891,"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":0.7439708113670349},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.6623278260231018},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.604841411113739},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5782397985458374},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.5591531991958618},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4677306115627289},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43122559785842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42799174785614014},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4212823212146759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3534785509109497},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09202522039413452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439708113670349},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.6623278260231018},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.604841411113739},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5782397985458374},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.5591531991958618},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4677306115627289},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43122559785842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42799174785614014},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4212823212146759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3534785509109497},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09202522039413452},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wcnc55385.2023.10118921","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcnc55385.2023.10118921","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Wireless Communications and Networking Conference (WCNC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1637570796","https://openalex.org/W2002182716","https://openalex.org/W2165291881","https://openalex.org/W2194775991","https://openalex.org/W2552465432","https://openalex.org/W2732044853","https://openalex.org/W2752796333","https://openalex.org/W2775336875","https://openalex.org/W2785562966","https://openalex.org/W2935711438","https://openalex.org/W2962676454","https://openalex.org/W2963182577","https://openalex.org/W2963799213","https://openalex.org/W2964098744","https://openalex.org/W2972354707","https://openalex.org/W3015268401","https://openalex.org/W3095497211","https://openalex.org/W3127686677","https://openalex.org/W3166791908","https://openalex.org/W3213872105","https://openalex.org/W3215615641","https://openalex.org/W4205788663","https://openalex.org/W4226042246","https://openalex.org/W4290713755","https://openalex.org/W4292972664","https://openalex.org/W4294567867","https://openalex.org/W6636885848","https://openalex.org/W6639363673","https://openalex.org/W6734035190","https://openalex.org/W6741057705"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W3161919736","https://openalex.org/W2176409448","https://openalex.org/W2374470469","https://openalex.org/W2352448339","https://openalex.org/W2787189739","https://openalex.org/W4387445182","https://openalex.org/W2159899134","https://openalex.org/W2363660481","https://openalex.org/W2039662546"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,56],"novel":[3],"neural":[4,172],"waveform":[5,87,173],"compression":[6,44],"method":[7,153],"to":[8,42,71,130,156],"catalyze":[9],"emerging":[10,171],"speech":[11,27,36,49,124],"semantic":[12,118],"communications.":[13,119],"By":[14],"introducing":[15],"nonlinear":[16,59],"transform":[17],"and":[18,29,53,82,96],"variational":[19],"modeling,":[20],"we":[21,126],"effectively":[22],"capture":[23,72],"the":[24,31,35,48,73,97,123,132,139,146,151],"dependencies":[25],"within":[26],"frames":[28],"estimate":[30],"probabilistic":[32,74],"distribution":[33,75],"of":[34,58,76],"feature":[37,100],"more":[38],"accurately,":[39],"giving":[40],"rise":[41],"better":[43],"performance.":[45],"In":[46],"particular,":[47],"signals":[50],"are":[51],"analyzed":[52],"synthesized":[54],"by":[55,80],"pair":[57],"transforms,":[60],"yielding":[61],"latent":[62,77,140],"features.":[63],"An":[64],"entropy":[65,83],"model":[66],"with":[67],"hyperprior":[68],"is":[69,101],"built":[70],"features,":[78],"followed":[79],"quantization":[81,136],"coding.":[84],"The":[85],"proposed":[86,152],"codec":[88,167],"can":[89,104],"be":[90,105],"optimized":[91,107],"flexibly":[92],"towards":[93],"arbitrary":[94],"rate,":[95],"other":[98],"appealing":[99],"that":[102,144],"it":[103],"easily":[106],"for":[108],"any":[109],"differentiable":[110],"loss":[111,115],"function,":[112],"including":[113],"perceptual":[114,148],"used":[116,162],"in":[117],"To":[120],"further":[121],"improve":[122],"quality,":[125],"incorporate":[127],"residual":[128],"coding":[129,158,174],"mitigate":[131],"degradation":[133],"arising":[134],"from":[135],"distortion":[137],"at":[138],"space.":[141],"Results":[142],"indicate":[143],"achieving":[145],"same":[147],"quality":[149],"score,":[150],"saves":[154],"up":[155],"27%":[157],"rate":[159],"than":[160],"widely":[161],"adaptive":[163],"multi-rate":[164],"wideband":[165],"(AMR-WB)":[166],"as":[168,170],"well":[169],"methods.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}