{"id":"https://openalex.org/W4311897894","doi":"https://doi.org/10.1109/taslp.2022.3224305","title":"End-to-End Multi-Modal Speech Recognition on an Air and Bone Conducted Speech Corpus","display_name":"End-to-End Multi-Modal Speech Recognition on an Air and Bone Conducted Speech Corpus","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4311897894","doi":"https://doi.org/10.1109/taslp.2022.3224305"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3224305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224305","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"],"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/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"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":"Mou Wang","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6476-2501","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","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":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-8662-3783","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, 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":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7694-193X","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]},{"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":"Susanto Rahardja","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","Singapore Institute of Technology, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0831-6934","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Singapore Institute of Technology, Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.713,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9392201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"513","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.7398630380630493},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.6857219934463501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6619446277618408},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5713798403739929},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4964140057563782},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3660491406917572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34821364283561707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398630380630493},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.6857219934463501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6619446277618408},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5713798403739929},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4964140057563782},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3660491406917572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34821364283561707},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3224305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224305","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5057566376","display_name":null,"funder_award_id":"62176211","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1544584678","https://openalex.org/W1828163288","https://openalex.org/W1974387177","https://openalex.org/W1992475611","https://openalex.org/W2039716246","https://openalex.org/W2062164080","https://openalex.org/W2127141656","https://openalex.org/W2147768505","https://openalex.org/W2153367543","https://openalex.org/W2166344203","https://openalex.org/W2245745904","https://openalex.org/W2284628133","https://openalex.org/W2327501763","https://openalex.org/W2584667682","https://openalex.org/W2766219058","https://openalex.org/W2774812352","https://openalex.org/W2790326622","https://openalex.org/W2797187289","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2894651928","https://openalex.org/W2901907199","https://openalex.org/W2936774411","https://openalex.org/W2962959469","https://openalex.org/W2972436155","https://openalex.org/W2987026005","https://openalex.org/W2991251958","https://openalex.org/W3003278325","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/W3115295666","https://openalex.org/W3160071434","https://openalex.org/W3160348851","https://openalex.org/W3162293946","https://openalex.org/W3196393301","https://openalex.org/W4224883138","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6675197204","https://openalex.org/W6695553435","https://openalex.org/W6732862412","https://openalex.org/W6739901393","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2549567669","https://openalex.org/W104838418","https://openalex.org/W1532889363","https://openalex.org/W4292416459","https://openalex.org/W2394331374","https://openalex.org/W4225253169","https://openalex.org/W2626842453","https://openalex.org/W2946426818","https://openalex.org/W4321180712","https://openalex.org/W627697492"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,36,78,137,154],"recognition":[2],"(ASR)":[3],"has":[4],"been":[5],"significantly":[6],"improved":[7],"in":[8,26],"the":[9,54,102,133,152,163,169,197,210],"past":[10],"years.":[11],"However,":[12],"most":[13],"robust":[14],"ASR":[15,58,109,117],"systems":[16,175],"are":[17,31,83,156],"based":[18,119],"on":[19,120],"air-conducted":[20],"(AC)":[21],"speech,":[22],"and":[23,43,75,92,135,143,182,204],"their":[24],"performances":[25],"low":[27,60],"signal-to-noise-ratio":[28],"(SNR)":[29],"conditions":[30],"not":[32],"satisfactory.":[33],"Bone-conducted":[34],"(BC)":[35],"is":[37,99],"intrinsically":[38],"insensitive":[39],"to":[40],"environmental":[41],"noise,":[42],"therefore":[44],"can":[45,207],"be":[46],"used":[47],"as":[48],"an":[49,57],"auxiliary":[50],"source":[51],"for":[52,105],"improving":[53],"performance":[55],"of":[56,151,213],"at":[59,190],"SNR.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,112],"first":[66],"develop":[67],"a":[68,86,114,121,140,144,187],"multi-modal":[69,81,115,123,171,183],"Mandarin":[70],"corpus,":[71],"which":[72],"contains":[73],"air-":[74],"bone-conducted":[76],"synchronized":[77],"(ABCS).":[79],"The":[80,126,148],"speeches":[82],"recorded":[84],"with":[85,89,159,176,201],"headset":[87],"equipped":[88],"both":[90],"AC":[91,134,178],"BC":[93,136,180],"microphones.":[94],"To":[95],"our":[96,205],"knowledge,":[97],"it":[98],"by":[100,139,162,186],"far":[101],"largest":[103],"corpus":[104],"conducting":[106],"bone":[107],"conduction":[108],"research.":[110],"Then,":[111],"propose":[113],"conformer":[116],"system":[118,128,172,185],"novel":[122],"transducer":[124],"(MMT).":[125],"proposed":[127,170],"extracts":[129],"semantic":[130,149],"embeddings":[131,150],"from":[132],"signals":[138],"conformer-based":[141],"encoder":[142],"transformer-based":[145],"truncated":[146],"decoder.":[147],"two":[153,198],"sources":[155],"fused":[157],"dynamically":[158],"adaptive":[160],"weights":[161],"MMT":[164],"module.":[165],"Experimental":[166],"results":[167],"demonstrate":[168],"outperforms":[173],"single-modal":[174],"either":[177],"or":[179],"modality":[181],"baseline":[184],"large":[188],"margin":[189],"various":[191],"SNR":[192],"levels.":[193],"It":[194],"also":[195],"shows":[196],"modalities":[199],"complement":[200],"each":[202],"other,":[203],"method":[206],"effectively":[208],"utilize":[209],"complementary":[211],"information":[212],"different":[214],"sources.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}