{"id":"https://openalex.org/W4372271612","doi":"https://doi.org/10.1109/icassp49357.2023.10095644","title":"Domain and Language Adaptation Using Heterogeneous Datasets for Wav2vec2.0-Based Speech Recognition of Low-Resource Language","display_name":"Domain and Language Adaptation Using Heterogeneous Datasets for Wav2vec2.0-Based Speech Recognition of Low-Resource Language","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372271612","doi":"https://doi.org/10.1109/icassp49357.2023.10095644"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095644","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":"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/A5015958922","display_name":"Kak Soky","orcid":"https://orcid.org/0000-0002-7014-147X"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kak Soky","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102757632","display_name":"Chenhui Chu","orcid":"https://orcid.org/0000-0001-9848-6384"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chenhui Chu","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University,Graduate School of Informatics,Sakyo-ku, Kyoto,Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5015958922"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":1.3892,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84509475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.9900000095367432,"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":0.8514872789382935},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7027980089187622},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.700222373008728},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6996147036552429},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.655925989151001},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6274794340133667},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6148082613945007},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6135414242744446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5814065933227539},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5780006647109985},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5537364482879639},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5388137698173523},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5362977385520935},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47132304310798645},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4379810094833374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514872789382935},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7027980089187622},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.700222373008728},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6996147036552429},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.655925989151001},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6274794340133667},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6148082613945007},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6135414242744446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5814065933227539},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5780006647109985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537364482879639},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5388137698173523},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5362977385520935},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47132304310798645},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4379810094833374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095644","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"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50729862","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100931474","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2896457183","https://openalex.org/W2936774411","https://openalex.org/W2979476256","https://openalex.org/W2979826702","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3113594615","https://openalex.org/W3122931219","https://openalex.org/W3155427814","https://openalex.org/W3180180466","https://openalex.org/W3196419581","https://openalex.org/W3198429080","https://openalex.org/W3198528147","https://openalex.org/W3202370288","https://openalex.org/W3211278025","https://openalex.org/W3213029956","https://openalex.org/W4205900877","https://openalex.org/W4286498414","https://openalex.org/W4296069120","https://openalex.org/W4297841331","https://openalex.org/W4311000453","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6787141514","https://openalex.org/W7034463875"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"We":[0],"address":[1],"the":[2,67,71,77,81,89,93,101,125,130,142],"effective":[3,51],"finetuning":[4,25,144],"of":[5,15,28,57,70,80,95,103,138],"a":[6,20,135],"large-scale":[7],"pretrained":[8,82],"model":[9,83],"for":[10,84],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"lowresource":[16],"languages":[17],"with":[18,45,63,120],"only":[19],"one-hour":[21],"matched":[22,44],"dataset.":[23],"The":[24],"is":[26,74,115,134],"composed":[27],"domain":[29,47,58,109,121,126],"adaptation":[30],"and":[31,34,60,111,123],"language":[32,61,113],"adaptation,":[33,52],"they":[35],"are":[36,43],"conducted":[37],"by":[38],"using":[39,92],"heterogeneous":[40],"datasets,":[41],"which":[42,133],"either":[46],"or":[48],"language.":[49],"For":[50],"we":[53],"incorporate":[54],"auxiliary":[55,72],"tasks":[56,73],"identification":[59,62,122],"multi-task":[64],"learning.":[65],"Moreover,":[66],"embedding":[68,128],"result":[69],"fused":[75],"to":[76],"encoder":[78],"output":[79],"ASR.":[85],"Experimental":[86],"evaluations":[87],"on":[88],"Khmer":[90],"ASR":[91],"corpus":[94],"ECCC":[96],"(the":[97],"Extraordinary":[98],"Chambers":[99],"in":[100],"Courts":[102],"Cambodia)":[104],"demonstrate":[105],"that":[106],"first":[107],"conducting":[108],"adaption":[110,114],"then":[112],"effective.":[116],"In":[117],"addition,":[118],"multi-tasking":[119],"fusing":[124],"ID":[127],"gives":[129],"best":[131],"performance,":[132],"CER":[136],"improvement":[137],"6.47%":[139],"absolute":[140],"from":[141],"baseline":[143],"method.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}