{"id":"https://openalex.org/W4224931274","doi":"https://doi.org/10.1109/icassp43922.2022.9746374","title":"Attention-Based Fusion for Bone-Conducted and Air-Conducted Speech Enhancement in the Complex Domain","display_name":"Attention-Based Fusion for Bone-Conducted and Air-Conducted Speech Enhancement in the Complex Domain","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931274","doi":"https://doi.org/10.1109/icassp43922.2022.9746374","pmid":"https://pubmed.ncbi.nlm.nih.gov/40313328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746374","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12045135","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":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":["Inner Mongolia University,Department of Computer Science,China","Department of Computer Science, Inner Mongolia University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Department of Computer Science,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Department of Computer Science, Inner Mongolia University, 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":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, 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":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2022","issue":null,"first_page":"7757","last_page":"7761"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6876605153083801},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.6153255701065063},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5714921951293945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44340482354164124},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08509516716003418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6876605153083801},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.6153255701065063},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5714921951293945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44340482354164124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08509516716003418},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746374","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:40313328","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40313328","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":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12045135","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12045135","pdf_url":null,"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":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12045135","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12045135","pdf_url":null,"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":"Proc IEEE Int Conf Acoust Speech Signal 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"}],"funders":[{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W1978141864","https://openalex.org/W1981157205","https://openalex.org/W2137793486","https://openalex.org/W2144205283","https://openalex.org/W2593658960","https://openalex.org/W2760471249","https://openalex.org/W2803417661","https://openalex.org/W2899699636","https://openalex.org/W2943554574","https://openalex.org/W2962866211","https://openalex.org/W2963446712","https://openalex.org/W2991251958","https://openalex.org/W2991361823","https://openalex.org/W2992628507","https://openalex.org/W2995343943","https://openalex.org/W3032514799","https://openalex.org/W3042800855","https://openalex.org/W3094897602","https://openalex.org/W3096408984","https://openalex.org/W3102334822","https://openalex.org/W3133637237","https://openalex.org/W3162109944","https://openalex.org/W3165227983","https://openalex.org/W3201698955","https://openalex.org/W6681491945","https://openalex.org/W7062130740"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Bone-conduction":[0],"(BC)":[1],"microphones":[2,36,59],"capture":[3],"speech":[4,100,118],"signals":[5,74],"by":[6,60],"converting":[7],"the":[8,11,29,53,91,94],"vibrations":[9],"of":[10,39,55,78,93],"human":[12],"skull":[13],"into":[14],"electrical":[15],"signals.":[16,107],"BC":[17,58,104],"sensors":[18],"are":[19,37,44],"insensitive":[20],"to":[21,46,51],"acoustic":[22],"noise,":[23],"but":[24,43],"limited":[25],"in":[26,122],"bandwidth.":[27],"On":[28],"other":[30,98],"hand,":[31],"conventional":[32,117],"or":[33],"air-conduction":[34],"(AC)":[35],"capable":[38],"capturing":[40],"full-band":[41],"speech,":[42],"susceptible":[45],"background":[47],"noise.":[48],"We":[49],"propose":[50],"combine":[52],"strengths":[54],"AC":[56,106],"and":[57,86,105],"employing":[61],"a":[62],"convolutional":[63],"recurrent":[64],"network":[65],"that":[66],"performs":[67],"complex":[68],"spectral":[69],"mapping.":[70],"To":[71],"better":[72,115],"utilize":[73],"from":[75],"both":[76],"kinds":[77],"microphone,":[79],"we":[80],"employ":[81],"attention-based":[82],"fusion":[83],"with":[84],"early-fusion":[85],"late-fusion":[87],"strategies.":[88],"Experiments":[89],"demonstrate":[90],"superiority":[92],"proposed":[95],"method":[96],"over":[97],"recent":[99],"enhancement":[101,111,119],"methods":[102],"combining":[103],"In":[108],"addition,":[109],"our":[110],"performance":[112],"is":[113],"significantly":[114],"than":[116],"counterparts,":[120],"especially":[121],"low":[123],"signal-to-noise":[124],"ratio":[125],"scenarios.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}