{"id":"https://openalex.org/W4297095639","doi":"https://doi.org/10.1109/taslp.2022.3209943","title":"Fusing Bone-Conduction and Air-Conduction Sensors for Complex-Domain Speech Enhancement","display_name":"Fusing Bone-Conduction and Air-Conduction Sensors for Complex-Domain Speech Enhancement","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4297095639","doi":"https://doi.org/10.1109/taslp.2022.3209943","pmid":"https://pubmed.ncbi.nlm.nih.gov/37124143"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3209943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209943","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10147322/pdf/nihms-1841164.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0003-3057-9060","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693230","display_name":"Xueliang Zhang","orcid":"https://orcid.org/0000-0002-0406-1105"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueliang Zhang","raw_affiliation_strings":["Department of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":"https://orcid.org/0000-0002-0406-1105","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2893,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95591532,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"30","issue":null,"first_page":"3134","last_page":"3143"},"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":0.9980999827384949,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7998493909835815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7396929860115051},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6421263813972473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.564993143081665},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45936861634254456},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4575885534286499},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4423998296260834},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4395906329154968},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.43836066126823425},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.43371254205703735},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4223594665527344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40176641941070557},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33780765533447266},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09920108318328857},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0794869065284729}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7998493909835815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7396929860115051},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6421263813972473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.564993143081665},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45936861634254456},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4575885534286499},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4423998296260834},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4395906329154968},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.43836066126823425},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.43371254205703735},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4223594665527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40176641941070557},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33780765533447266},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09920108318328857},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0794869065284729},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2022.3209943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209943","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:37124143","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37124143","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10147322","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10147322","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10147322/pdf/nihms-1841164.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:10147322","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10147322","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10147322/pdf/nihms-1841164.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"},{"id":"https://openalex.org/G6100668328","display_name":null,"funder_award_id":"DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4297095639.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1677182931","https://openalex.org/W1974387177","https://openalex.org/W1981157205","https://openalex.org/W2040214655","https://openalex.org/W2081498888","https://openalex.org/W2133765057","https://openalex.org/W2137793486","https://openalex.org/W2141998673","https://openalex.org/W2144205283","https://openalex.org/W2160800342","https://openalex.org/W2165899180","https://openalex.org/W2166344203","https://openalex.org/W2284177371","https://openalex.org/W2519091744","https://openalex.org/W2593414223","https://openalex.org/W2740715668","https://openalex.org/W2760471249","https://openalex.org/W2802023636","https://openalex.org/W2803417661","https://openalex.org/W2894651928","https://openalex.org/W2899617931","https://openalex.org/W2899699636","https://openalex.org/W2952613166","https://openalex.org/W2962765321","https://openalex.org/W2962793481","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2963446712","https://openalex.org/W2964135678","https://openalex.org/W2970574533","https://openalex.org/W2984353870","https://openalex.org/W2991251958","https://openalex.org/W2991361823","https://openalex.org/W2992628507","https://openalex.org/W2995343943","https://openalex.org/W3031696893","https://openalex.org/W3032514799","https://openalex.org/W3042800855","https://openalex.org/W3094897602","https://openalex.org/W3096408984","https://openalex.org/W3096641561","https://openalex.org/W3102334822","https://openalex.org/W3103294501","https://openalex.org/W3125868443","https://openalex.org/W3133637237","https://openalex.org/W3134695619","https://openalex.org/W3136020068","https://openalex.org/W3162109944","https://openalex.org/W3165227983","https://openalex.org/W3201698955","https://openalex.org/W3212386989","https://openalex.org/W4224931274","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6681491945","https://openalex.org/W6713394505","https://openalex.org/W6739901393","https://openalex.org/W6767327284","https://openalex.org/W7062130740"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2738829087","https://openalex.org/W2231565466","https://openalex.org/W2373767407","https://openalex.org/W4200596008","https://openalex.org/W2248536413","https://openalex.org/W2383417046","https://openalex.org/W4386336391","https://openalex.org/W3217417050","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,24,34],"aims":[2],"to":[3,18,21,42,76,131,154,178],"improve":[4],"the":[5,52,78,95,100,105,125,140,171],"listening":[6],"quality":[7],"and":[8,82,85,109,112,158,162],"intelligibility":[9],"of":[10,47,80,107,142],"noisy":[11],"speech":[12,23,33,65,91,164,169],"in":[13,25,118,135],"adverse":[14],"environments.":[15],"It":[16],"proves":[17],"be":[19],"challenging":[20],"perform":[22,86],"very":[26,146],"low":[27,136],"signal-to-noise":[28],"ratio":[29],"(SNR)":[30],"conditions.":[31,120,138],"Conventional":[32],"utilizes":[35],"air-conduction":[36],"(AC)":[37],"microphones,":[38],"which":[39],"are":[40,58],"sensitive":[41],"background":[43],"noise":[44],"but":[45,63],"capable":[46],"capturing":[48],"full-band":[49],"signals.":[50,165],"On":[51],"other":[53],"hand,":[54],"bone-conduction":[55],"(BC)":[56],"sensors":[57],"unaffected":[59],"by":[60],"acoustic":[61],"noise,":[62],"recorded":[64,160],"has":[66],"limited":[67],"bandwidth.":[68],"This":[69],"study":[70],"proposes":[71],"an":[72],"attention-based":[73],"fusion":[74,127],"method":[75,128],"combine":[77],"strengths":[79],"AC":[81,108,161,168],"BC":[83,110,143,163],"signals":[84],"complex":[87],"spectral":[88],"mapping":[89],"for":[90],"enhancement.":[92],"Experiments":[93],"on":[94],"EMSB":[96],"dataset":[97],"demonstrate":[98],"that":[99,124],"proposed":[101],"approach":[102],"effectively":[103],"leverages":[104],"advantages":[106],"sensors,":[111],"outperforms":[113],"a":[114,151],"recent":[115],"time-domain":[116],"baseline":[117],"all":[119],"We":[121],"also":[122],"show":[123],"sensor":[126],"is":[129,145],"superior":[130],"single-sensor":[132],"counterparts,":[133],"especially":[134],"SNR":[137],"As":[139],"amount":[141],"data":[144],"limited,":[147],"we":[148,174],"additionally":[149],"propose":[150],"semi-supervised":[152],"technique":[153],"utilize":[155],"both":[156],"parallelly":[157],"unparallely":[159],"With":[166],"additional":[167],"from":[170],"AISHELL-1":[172],"dataset,":[173],"achieve":[175],"similar":[176],"performance":[177],"supervised":[179],"learning":[180],"with":[181],"only":[182],"50%":[183],"parallel":[184],"data.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}