{"id":"https://openalex.org/W4224923672","doi":"https://doi.org/10.1109/icassp43922.2022.9747306","title":"End-To-End Multi-Modal Speech Recognition with Air and Bone Conducted Speech","display_name":"End-To-End Multi-Modal Speech Recognition with Air and Bone Conducted Speech","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224923672","doi":"https://doi.org/10.1109/icassp43922.2022.9747306"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747306","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"],"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/A5114910944","display_name":"Junqi Chen","orcid":"https://orcid.org/0000-0001-8662-3783"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqi Chen","raw_affiliation_strings":["Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","Research & Development Institute of Northwestern Polytechnical University in Shenzhen, China","CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Research & Development Institute of Northwestern Polytechnical University in Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Mou Wang","raw_affiliation_strings":["Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","School of Computing, National University of Singapore & NUS Research Institute in Chongqing","CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computing, National University of Singapore & NUS Research Institute in Chongqing","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","Research & Development Institute of Northwestern Polytechnical University in Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Research & Development Institute of Northwestern Polytechnical University in Shenzhen, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101695947","display_name":"Zhiyong Huang","orcid":"https://orcid.org/0000-0002-6329-4427"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhiyong Huang","raw_affiliation_strings":["National University of Singapore &#x0026; NUS Research Institute in Chongqing,School of Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore &#x0026; NUS Research Institute in Chongqing,School of Computing","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,CIAIC, School of Marine Science and Technology,China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"CIAIC, School of Marine Science and Technology, Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6052","last_page":"6056"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443495988845825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7019791007041931},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4889039099216461},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4818173944950104},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.47558605670928955},{"id":"https://openalex.org/keywords/turbofan","display_name":"Turbofan","score":0.4267879128456116},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.413278728723526},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4131869375705719},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.30773699283599854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28673964738845825},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12563171982765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443495988845825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7019791007041931},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4889039099216461},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4818173944950104},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.47558605670928955},{"id":"https://openalex.org/C110050840","wikidata":"https://www.wikidata.org/wiki/Q654051","display_name":"Turbofan","level":2,"score":0.4267879128456116},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.413278728723526},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4131869375705719},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30773699283599854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28673964738845825},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12563171982765198},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747306","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747306","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W2039716246","https://openalex.org/W2062164080","https://openalex.org/W2289394825","https://openalex.org/W2766219058","https://openalex.org/W2797187289","https://openalex.org/W2809941692","https://openalex.org/W2901907199","https://openalex.org/W2936774411","https://openalex.org/W2972436155","https://openalex.org/W2987026005","https://openalex.org/W2991251958","https://openalex.org/W3011234510","https://openalex.org/W3095095816","https://openalex.org/W3097777922","https://openalex.org/W3102334822","https://openalex.org/W3103003256","https://openalex.org/W3106423890","https://openalex.org/W3133637237","https://openalex.org/W3160071434","https://openalex.org/W3162293946","https://openalex.org/W3163142165","https://openalex.org/W3196393301"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340","https://openalex.org/W4229451372","https://openalex.org/W2113211312"],"abstract_inverted_index":{"Improving":[0],"the":[1,60,95,108,123,126,166,175],"performance":[2,30,62],"of":[3,58,107,125,143,169],"automatic":[4],"speech":[5,34,47,80,173],"recognition":[6,81],"(ASR)":[7],"in":[8,40],"adverse":[9],"acoustic":[10],"environments":[11,67],"is":[12,35,48],"a":[13,56,77,85,89,116,132,139,148,161],"long-term":[14],"tough":[15],"task.":[16],"Although":[17],"many":[18],"robust":[19],"ASR":[20,61],"systems":[21],"based":[22],"on":[23,152],"conventional":[24],"microphones":[25],"have":[26],"been":[27],"developed,":[28],"their":[29],"with":[31],"air-conducted":[32],"(AC)":[33],"still":[36],"far":[37],"from":[38,98],"satisfactory":[39],"low":[41,65],"signal-to-noise-ratio":[42],"(SNR)":[43],"environments.":[44],"Bone-conducted":[45],"(BC)":[46],"relatively":[49],"insensitive":[50],"to":[51,93],"ambient":[52],"noise,":[53],"and":[54,88,100,113,156,171],"has":[55],"potential":[57],"promoting":[59],"at":[63],"such":[64],"SNR":[66,135],"as":[68,174],"an":[69],"auxiliary":[70],"source.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"conformer-based":[78],"multi-modal":[79,118,162],"system.":[82],"It":[83],"uses":[84],"conformer":[86],"encoder":[87],"transformer-based":[90],"truncated":[91],"decoder":[92],"extract":[94],"semantic":[96,105],"information":[97,106],"AC":[99,153,170],"BC":[101,172],"channels":[102,110],"respectively.":[103],"The":[104],"two":[109],"are":[111],"re-weighted":[112],"integrated":[114],"by":[115],"novel":[117],"transducer.":[119],"Experimental":[120],"results":[121],"show":[122],"effectiveness":[124],"proposed":[127],"method.":[128],"For":[129],"example,":[130],"given":[131],"0":[133],"dB":[134],"environment,":[136],"it":[137],"yields":[138],"character":[140],"error":[141],"rate":[142],"over":[144,157],"59.0%":[145],"lower":[146,159],"than":[147,160],"noise-robust":[149],"baseline":[150,163],"conducted":[151],"channel":[154],"only,":[155],"12.7%":[158],"that":[164],"takes":[165],"concatenated":[167],"features":[168],"input.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
