{"id":"https://openalex.org/W7131422112","doi":"https://doi.org/10.1109/jiot.2026.3667945","title":"A Neural Codec for Bone-Conducted Speech With Joint Denoising and Bandwidth Extension","display_name":"A Neural Codec for Bone-Conducted Speech With Joint Denoising and Bandwidth Extension","publication_year":2026,"publication_date":"2026-02-25","ids":{"openalex":"https://openalex.org/W7131422112","doi":"https://doi.org/10.1109/jiot.2026.3667945"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2026.3667945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3667945","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":null,"display_name":"Xiaolong Hu","orcid":"https://orcid.org/0000-0002-4310-7751"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Hu","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-4310-7751","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126838006","display_name":"Zhe Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Chen","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0002-6822-9667","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080791396","display_name":"Fuliang Yin","orcid":"https://orcid.org/0000-0003-2642-8489"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuliang Yin","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0003-2642-8489","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18356305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"10","first_page":"21596","last_page":"21612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.32589998841285706,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.32589998841285706,"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":0.25619998574256897,"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/T10320","display_name":"Neural Networks and Applications","score":0.10100000351667404,"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/speech-coding","display_name":"Speech coding","score":0.5490000247955322},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5472999811172485},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.545199990272522},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.5404999852180481},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5152000188827515},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5069000124931335},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4672999978065491},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4456999897956848},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43869999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871399998664856},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.589900016784668},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5472999811172485},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.545199990272522},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.5404999852180481},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5152000188827515},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43869999051094055},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.41850000619888306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.33640000224113464},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.32179999351501465},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.3127000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2026.3667945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3667945","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/G1953956083","display_name":null,"funder_award_id":"62271103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6409499632","display_name":"\u5206\u5e03\u5f0f\u9ea6\u514b\u98ce\u9635\u5217\u6821\u51c6\u65b0\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61871066","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6917949686","display_name":null,"funder_award_id":"DUT17LAB04","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"Internet":[1],"of":[2,53,92,119,174,215],"Things":[3],"(IoT)":[4],"communication":[5],"scenarios":[6],"such":[7],"as":[8,62],"wearable":[9],"and":[10,40,56,80,114,134,163,185,224],"industrial":[11],"systems":[12],"operating":[13],"in":[14,45,84,108,143,228],"extremely":[15],"noisy":[16],"environments,":[17],"Bone-Conducted":[18],"Microphone":[19],"(BCM)":[20],"speech":[21,36,86,93,176,183,226],"inevitably":[22],"suffers":[23],"from":[24],"noise":[25],"interference.":[26],"To":[27,88],"address":[28],"this":[29,46,66],"issue,":[30],"a":[31,68,96,148,191],"neural":[32],"codec":[33],"for":[34,138,222],"bone-conducted":[35],"with":[37,167],"joint":[38],"denoising":[39],"bandwidth":[41],"extension":[42],"is":[43,60,73,101,124,153],"proposed":[44,154,179,217],"paper.":[47],"Speciffcally,":[48],"an":[49,157],"encoder\u2013decoder":[50],"architecture":[51,160,207],"composed":[52],"the":[54,57,63,85,90,105,111,128,139,175,205,213,216],"MP-SENet":[55],"BigVGAN":[58],"vocoder":[59],"built":[61],"backbone.":[64],"On":[65],"basis,":[67],"Forward":[69],"Time-Frequency":[70,98],"Transformer":[71,99],"(FTM)":[72],"introduced":[74],"to":[75,103,126,130,155,170,204],"effectively":[76],"capture":[77,131],"both":[78],"local":[79],"global":[81],"time-frequency":[82,120],"dependencies":[83,133],"signal.":[87,177],"improve":[89],"capacity":[91],"signal":[94],"modeling,":[95],"Backward":[97],"(BTM)":[100],"presented":[102],"model":[104],"information":[106],"flow":[107],"reverse,":[109],"complementing":[110],"forward":[112],"modeling":[113,144],"enabling":[115],"more":[116],"comprehensive":[117],"extraction":[118],"features.":[121],"Subsequently,":[122],"KalmanNet":[123],"designed":[125],"enhance":[127],"ability":[129],"temporal":[132],"dynamic":[135],"information,":[136],"compensating":[137],"transformer\u2019s":[140],"limited":[141],"effectiveness":[142],"continuous":[145],"dynamics.":[146],"Finally,":[147],"Dual-Path":[149],"Magnitude-Phase":[150],"(DPMP)":[151],"module":[152],"feature":[156],"interactive":[158],"dual-stream":[159],"where":[161],"magnitude":[162],"phase":[164],"streams":[165],"communicate":[166],"each":[168],"other":[169],"supplement":[171],"high-frequency":[172],"components":[173],"The":[178],"method":[180],"enables":[181],"simultaneous":[182],"encoding":[184],"enhancement":[186],"under":[187],"different":[188,199],"SNRs":[189],"using":[190],"single":[192],"network.":[193],"Furthermore,":[194],"it":[195],"supports":[196],"coding":[197],"at":[198],"bitrates":[200],"without":[201],"requiring":[202],"modifications":[203],"network":[206],"or":[208],"retraining.":[209],"Simulation":[210],"experiments":[211],"demonstrate":[212],"feasibility":[214],"approach,":[218],"highlighting":[219],"its":[220],"potential":[221],"robust":[223],"efficient":[225],"transmission":[227],"IoT-enabled":[229],"communication.":[230]},"counts_by_year":[],"updated_date":"2026-05-09T06:09:20.037420","created_date":"2026-02-26T00:00:00"}