{"id":"https://openalex.org/W4375869316","doi":"https://doi.org/10.1109/icassp49357.2023.10095177","title":"MADI: Inter-Domain Matching and Intra-Domain Discrimination for Cross-Domain Speech Recognition","display_name":"MADI: Inter-Domain Matching and Intra-Domain Discrimination for Cross-Domain Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869316","doi":"https://doi.org/10.1109/icassp49357.2023.10095177"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101880813","display_name":"Jiaming Zhou","orcid":"https://orcid.org/0000-0002-0043-3645"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Zhou","raw_affiliation_strings":["Nankai University,Tianjin,China","Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052465353","display_name":"Shiwan Zhao","orcid":"https://orcid.org/0000-0001-5068-025X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwan Zhao","raw_affiliation_strings":["Nankai University,Tianjin,China","Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101443742","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0002-7152-3621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628448","display_name":"Guoqing Zhao","orcid":"https://orcid.org/0000-0001-7130-7147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoqing Zhao","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088716214","display_name":"Yong Qin","orcid":"https://orcid.org/0000-0002-6519-8316"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Qin","raw_affiliation_strings":["Nankai University,Tianjin,China","Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nankai University,Tianjin,China","institution_ids":["https://openalex.org/I205237279"]},{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"1","last_page":"5"},"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":0.9988999962806702,"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":0.998199999332428,"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/domain-adaptation","display_name":"Domain adaptation","score":0.8118974566459656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072930574417114},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7718555927276611},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.711669921875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6002773642539978},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5737156867980957},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.5552456378936768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5429600477218628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4881483018398285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3542993366718292},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27423155307769775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10731533169746399},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08609762787818909}],"concepts":[{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.8118974566459656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072930574417114},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7718555927276611},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.711669921875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6002773642539978},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5737156867980957},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.5552456378936768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5429600477218628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4881483018398285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3542993366718292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27423155307769775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10731533169746399},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08609762787818909},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2798453135","https://openalex.org/W2933224119","https://openalex.org/W2946812986","https://openalex.org/W2962684181","https://openalex.org/W2964288524","https://openalex.org/W3005680577","https://openalex.org/W3015723617","https://openalex.org/W3015838662","https://openalex.org/W3097778103","https://openalex.org/W3109233242","https://openalex.org/W3144810982","https://openalex.org/W3162061711","https://openalex.org/W3194701944","https://openalex.org/W3197285286","https://openalex.org/W3197478142","https://openalex.org/W3198608154","https://openalex.org/W3211278025","https://openalex.org/W4287110655","https://openalex.org/W4287124998","https://openalex.org/W4296068785","https://openalex.org/W4296068790","https://openalex.org/W6688325169","https://openalex.org/W6763066025","https://openalex.org/W6770655456","https://openalex.org/W6774314701","https://openalex.org/W6787542208","https://openalex.org/W6796863536"],"related_works":["https://openalex.org/W2280198878","https://openalex.org/W2140460368","https://openalex.org/W4321649381","https://openalex.org/W4375869316","https://openalex.org/W2902524664","https://openalex.org/W2947177396","https://openalex.org/W2771673059","https://openalex.org/W2137148130","https://openalex.org/W4300330203","https://openalex.org/W4283012013"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"usually":[5],"suffers":[6],"from":[7,37],"performance":[8,28],"degradation":[9],"when":[10],"applied":[11],"to":[12,17,25,40],"a":[13,75],"new":[14],"domain":[15,18,21,33],"due":[16],"shift.":[19],"Unsupervised":[20],"adaptation":[22],"(UDA)":[23],"aims":[24],"improve":[26,45],"the":[27,30,38,41,54,57,67,90,106,110,117],"on":[29,52,105,123],"unlabeled":[31],"target":[32,42,60],"by":[34,93,99,128],"transferring":[35],"knowledge":[36],"source":[39,58],"domain.":[43],"To":[44],"transferability,":[46],"existing":[47],"UDA":[48,77],"approaches":[49],"mainly":[50],"focus":[51],"matching":[53,96],"distributions":[55],"of":[56,112],"and":[59,84,97,125,130],"domains":[61],"globally":[62],"and/or":[63],"locally,":[64],"while":[65],"ignoring":[66],"model":[68,91],"discriminability.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"novel":[76],"approach":[78],"for":[79],"ASR":[80,127],"via":[81],"inter-domain":[82,95],"MAtching":[83],"intra-domain":[85,100],"DIscrimination":[86],"(MADI),":[87],"which":[88],"improves":[89],"transferability":[92],"fine-grained":[94],"discriminability":[98],"contrastive":[101],"discrimination":[102],"simultaneously.":[103],"Evaluations":[104],"Libri-Adapt":[107],"dataset":[108],"demonstrate":[109],"effectiveness":[111],"our":[113],"approach.":[114],"MADI":[115],"reduces":[116],"relative":[118],"word":[119],"error":[120],"rate":[121],"(WER)":[122],"cross-device":[124],"cross-environment":[126],"17.7%":[129],"22.8%,":[131],"respectively.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}