{"id":"https://openalex.org/W4391021653","doi":"https://doi.org/10.1109/asru57964.2023.10389721","title":"Domain Adaptation by Data Distribution Matching Via Submodularity For Speech Recognition","display_name":"Domain Adaptation by Data Distribution Matching Via Submodularity For Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021653","doi":"https://doi.org/10.1109/asru57964.2023.10389721"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389721","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-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/A5109365728","display_name":"Yusuke Shinohara","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Shinohara","raw_affiliation_strings":["LY Corporation,Japan","LY Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"LY Corporation,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LY Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109365728"],"corresponding_institution_ids":["https://openalex.org/I4210096607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19179835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/1503.03535","issue":null,"first_page":"1","last_page":"7"},"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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/submodular-set-function","display_name":"Submodular set function","score":0.7903709411621094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7385059595108032},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.713689923286438},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7041400671005249},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6976392865180969},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.531679093837738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48525404930114746},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.48206764459609985},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3758057951927185},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.368069589138031},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3516736626625061},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17225179076194763},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15932300686836243},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07490989565849304}],"concepts":[{"id":"https://openalex.org/C178621042","wikidata":"https://www.wikidata.org/wiki/Q7631710","display_name":"Submodular set function","level":2,"score":0.7903709411621094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7385059595108032},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.713689923286438},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7041400671005249},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6976392865180969},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.531679093837738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48525404930114746},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48206764459609985},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3758057951927185},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.368069589138031},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3516736626625061},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17225179076194763},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15932300686836243},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07490989565849304},{"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389721","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1576820654","https://openalex.org/W1828163288","https://openalex.org/W1898824936","https://openalex.org/W1915251500","https://openalex.org/W2062366414","https://openalex.org/W2399978376","https://openalex.org/W2500139799","https://openalex.org/W2756073160","https://openalex.org/W2911936302","https://openalex.org/W2930957955","https://openalex.org/W2963240019","https://openalex.org/W2963366389","https://openalex.org/W2972880214","https://openalex.org/W3006752097","https://openalex.org/W3008037978","https://openalex.org/W3016234571","https://openalex.org/W3026041220","https://openalex.org/W3094667432","https://openalex.org/W3097777922","https://openalex.org/W3112702554","https://openalex.org/W3152221657","https://openalex.org/W3162244132","https://openalex.org/W3197661863","https://openalex.org/W3198694222","https://openalex.org/W3205788551","https://openalex.org/W3211278025","https://openalex.org/W4205509257","https://openalex.org/W4210811812","https://openalex.org/W4286562652","https://openalex.org/W4297841923","https://openalex.org/W4327993492","https://openalex.org/W4385569885","https://openalex.org/W4388017359","https://openalex.org/W6638749077","https://openalex.org/W6639825529","https://openalex.org/W6752194381","https://openalex.org/W6782045920","https://openalex.org/W6839744984","https://openalex.org/W6847363464","https://openalex.org/W6850533807"],"related_works":["https://openalex.org/W1595919516","https://openalex.org/W2945022594","https://openalex.org/W2194604332","https://openalex.org/W4379619607","https://openalex.org/W1989453388","https://openalex.org/W2922450688","https://openalex.org/W4313349366","https://openalex.org/W3141561286","https://openalex.org/W4288560659","https://openalex.org/W2125653933"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,15,20,38,46,81,90,103,123,131,139],"problem":[3,26],"of":[4,19,111],"building":[5],"a":[6,32,69,85,97,109,119],"domain-specific":[7,33],"speech":[8],"recognition":[9],"model":[10,35,47,86,140],"given":[11,39],"some":[12],"text":[13],"from":[14,37,73],"target":[16],"domain.":[17],"One":[18],"most":[21],"popular":[22],"approaches":[23],"to":[24,79],"this":[25,58],"is":[27,71,87,100],"shallow":[28,42],"fusion,":[29],"which":[30,52],"incorporates":[31],"language":[34],"build":[36],"text.":[40],"However,":[41],"fusion":[43],"significantly":[44],"increases":[45],"size":[48,141],"and":[49,84,142],"inference":[50,143],"cost,":[51],"makes":[53],"its":[54],"deployment":[55],"harder.":[56],"In":[57],"paper,":[59],"we":[60,114],"propose":[61],"domain":[62],"adaptation":[63],"by":[64],"data":[65,78],"distribution":[66],"matching,":[67],"where":[68,113],"subset":[70,104],"selected":[72],"an":[74],"existing":[75],"multi-domain":[76],"training":[77],"match":[80],"target-domain":[82],"distribution,":[83],"fine-tuned":[88],"on":[89,107],"subset.":[91],"A":[92],"submodular":[93],"optimization":[94],"algorithm":[95],"with":[96,130],"novel":[98],"extension":[99],"employed":[101],"for":[102],"selection.":[105],"Experiments":[106],"LibriSpeech,":[108],"corpus":[110],"audiobooks,":[112],"treat":[115],"each":[116],"book":[117],"as":[118],"domain,":[120],"show":[121],"that":[122],"proposed":[124],"distribution-matching":[125],"approach":[126],"achieves":[127],"WERs":[128],"equivalent":[129],"conventional":[132],"shallow-fusion":[133],"approach,":[134],"without":[135],"any":[136],"increase":[137],"in":[138],"cost.":[144]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}