{"id":"https://openalex.org/W4319862695","doi":"https://doi.org/10.1109/slt54892.2023.10023233","title":"Domain Adaptation of Low-Resource Target-Domain Models Using Well-Trained ASR Conformer Models","display_name":"Domain Adaptation of Low-Resource Target-Domain Models Using Well-Trained ASR Conformer Models","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862695","doi":"https://doi.org/10.1109/slt54892.2023.10023233"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023233","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5059299971","display_name":"Vrunda N. Sukhadia","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vrunda N. Sukhadia","raw_affiliation_strings":["IIT Madras,Speech Lab,Dept. of Electrical Engineering,Chennai,India","Dept. of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Dept. of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Dept. of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["IIT Madras,Speech Lab,Dept. of Electrical Engineering,Chennai,India","Dept. of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Dept. of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Dept. of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24676775"],"apc_list":null,"apc_paid":null,"fwci":1.0889,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77753541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"301"},"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":0.9995999932289124,"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":0.9929999709129333,"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/encoder","display_name":"Encoder","score":0.8231688141822815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914455533027649},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6902720928192139},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5880096554756165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4987831115722656},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4868178069591522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4638158679008484},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4375956058502197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4352497458457947},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4110598564147949},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1608087420463562},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08154451847076416}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.8231688141822815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914455533027649},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6902720928192139},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5880096554756165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4987831115722656},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4868178069591522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4638158679008484},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4375956058502197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4352497458457947},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4110598564147949},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1608087420463562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08154451847076416},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023233","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2165698076","https://openalex.org/W2786459654","https://openalex.org/W2936774411","https://openalex.org/W3035390927","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3152221657","https://openalex.org/W3196321886","https://openalex.org/W3197507772","https://openalex.org/W3197580070","https://openalex.org/W3197681820","https://openalex.org/W3198587774","https://openalex.org/W3198694222","https://openalex.org/W3198771897","https://openalex.org/W3207558756","https://openalex.org/W3209059054","https://openalex.org/W4299518610","https://openalex.org/W6682132143","https://openalex.org/W6761305474","https://openalex.org/W6769263558","https://openalex.org/W6777337586","https://openalex.org/W6780218876","https://openalex.org/W6785336157","https://openalex.org/W6787587704","https://openalex.org/W6791960491","https://openalex.org/W6793527289","https://openalex.org/W6796554684"],"related_works":["https://openalex.org/W3034688404","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W2955455867","https://openalex.org/W4321649381","https://openalex.org/W3180787869","https://openalex.org/W2997645659","https://openalex.org/W3203792196","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"In":[0,48],"encoder-decoder":[1],"framework":[2],"for":[3,67,86],"Automatic":[4],"Speech":[5],"Recognition":[6],"(ASR)":[7],"systems,":[8],"the":[9,12,20,23,32,35,39,45,51,55,90,96,103,110,114],"decoder":[10],"of":[11,25,38,58,70,92,105,126],"well-trained":[13,40,60,97],"ASR":[14,41,61,98],"model":[15,42,62,133,137],"is":[16],"largely":[17],"tuned":[18],"towards":[19],"source-domain,":[21],"hurting":[22],"performance":[24,116],"target-domain":[26,76,115,135],"models":[27],"in":[28],"vanilla":[29],"transfer-learning.":[30],"On":[31],"other":[33],"hand,":[34],"encoder":[36,56,84,100],"layers":[37,57,85],"mainly":[43],"capture":[44],"acoustic":[46],"characteristics.":[47],"this":[49],"paper,":[50],"embeddings":[52,88],"tapped":[53],"from":[54],"a":[59,71],"are":[63],"used":[64],"as":[65],"features":[66,112],"domain":[68],"adaptation":[69],"downstream":[72],"low":[73],"resource":[74],"Conformer":[75,136],"model.":[77],"We":[78],"do":[79],"ablation":[80],"studies":[81],"on":[82,109],"optimal":[83],"tapping":[87],"and":[89,134],"effect":[91],"freezing":[93],"or":[94],"updating":[95],"model's":[99],"layers.":[101],"Lastly,":[102],"application":[104],"Spectral":[106],"Augmentation":[107],"(SpecAug)":[108],"proposed":[111,119],"improves":[113],"further.":[117],"The":[118],"method":[120],"reports":[121],"an":[122],"average":[123],"relative":[124],"improvement":[125],"~40%":[127],"over":[128],"baseline":[129],"with":[130],"different":[131],"source-domain":[132],"combinations.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2023-02-11T00:00:00"}