{"id":"https://openalex.org/W4385484929","doi":"https://doi.org/10.1109/icasspw59220.2023.10193570","title":"Efficient Utilization of Large Pre-Trained Models for Low Resource ASR","display_name":"Efficient Utilization of Large Pre-Trained Models for Low Resource ASR","publication_year":2023,"publication_date":"2023-06-04","ids":{"openalex":"https://openalex.org/W4385484929","doi":"https://doi.org/10.1109/icasspw59220.2023.10193570"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw59220.2023.10193570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5055945494","display_name":"Peter Vieting","orcid":"https://orcid.org/0000-0002-3582-5382"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Vieting","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060461441","display_name":"Christoph L\u00fcscher","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph L\u00fcscher","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055261445","display_name":"Julian Dierkes","orcid":"https://orcid.org/0000-0003-4322-4699"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Dierkes","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schl\u00fcter","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]},{"id":"https://openalex.org/I99977706","display_name":"FH Aachen","ror":"https://ror.org/04tqgg260","country_code":"DE","type":"education","lineage":["https://openalex.org/I99977706"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","AppTek GmbH, Aachen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Human Language Technology and Pattern Recognition Group,Computer Science Department,Aachen,Germany,52074","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"AppTek GmbH, Aachen, Germany","institution_ids":["https://openalex.org/I99977706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64314771,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":0.9976000189781189,"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":0.8691450357437134},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.5885940194129944},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5452256202697754},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5278099775314331},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5195636749267578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.500119686126709},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4907151460647583},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48888128995895386},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48610806465148926},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4809945821762085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4779227375984192},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4761597812175751},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.28217071294784546},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08254870772361755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8691450357437134},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.5885940194129944},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5452256202697754},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5278099775314331},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5195636749267578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.500119686126709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4907151460647583},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48888128995895386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48610806465148926},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4809945821762085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4779227375984192},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4761597812175751},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28217071294784546},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08254870772361755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw59220.2023.10193570","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw59220.2023.10193570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311419","display_name":"Ministry of Health","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2187428966","https://openalex.org/W2291975472","https://openalex.org/W2905489173","https://openalex.org/W2933138175","https://openalex.org/W2962728618","https://openalex.org/W2973049979","https://openalex.org/W3036601975","https://openalex.org/W3137720654","https://openalex.org/W3160799772","https://openalex.org/W3167207712","https://openalex.org/W3198429080","https://openalex.org/W3198771897","https://openalex.org/W3203140070","https://openalex.org/W3212799896","https://openalex.org/W4206375145","https://openalex.org/W4225501245","https://openalex.org/W4226380987","https://openalex.org/W4281492411","https://openalex.org/W4297808394","https://openalex.org/W4297841844","https://openalex.org/W4307539315","https://openalex.org/W6757717501","https://openalex.org/W6779919476","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6792432315","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3095487414","https://openalex.org/W3035557009","https://openalex.org/W4288048773","https://openalex.org/W2901026139","https://openalex.org/W2955172689","https://openalex.org/W2341113105","https://openalex.org/W3204418343","https://openalex.org/W3132602785","https://openalex.org/W3046182208","https://openalex.org/W2186589590"],"abstract_inverted_index":{"Unsupervised":[0],"representation":[1],"learning":[2],"has":[3],"recently":[4],"helped":[5],"automatic":[6],"speech":[7,52],"recognition":[8],"(ASR)":[9],"to":[10,25,29,79,82],"tackle":[11],"tasks":[12],"with":[13],"limited":[14],"labeled":[15],"data.":[16,132],"Following":[17],"this,":[18],"hardware":[19],"limitations":[20],"and":[21,37,60,90,97,121,123],"applications":[22],"give":[23],"rise":[24],"the":[26,55,64,101],"question":[27],"how":[28,78],"take":[30],"advantage":[31],"of":[32,66,73,112,119,129],"large":[33,74],"pre-trained":[34,75],"models":[35],"efficiently":[36],"reduce":[38],"their":[39],"complexity.":[40],"In":[41],"this":[42],"work,":[43],"we":[44],"study":[45],"a":[46,83],"challenging":[47],"low":[48],"resource":[49],"conversational":[50],"telephony":[51,85],"corpus":[53],"from":[54],"medical":[56],"domain":[57],"in":[58],"Vietnamese":[59],"German.":[61],"We":[62,99],"show":[63],"benefits":[65],"using":[67,107],"unsupervised":[68],"techniques":[69],"beyond":[70],"simple":[71],"fine-tuning":[72],"models,":[76],"discuss":[77],"adapt":[80],"them":[81],"practical":[84],"task":[86],"including":[87],"bandwidth":[88],"transfer":[89],"investigate":[91],"different":[92],"data":[93],"conditions":[94],"for":[95],"pre-training":[96,108],"fine-tuning.":[98],"outperform":[100],"project":[102],"baselines":[103],"by":[104,117,125],"22%":[105],"relative":[106],"techniques.":[109],"Further":[110],"gains":[111],"29%":[113],"can":[114],"be":[115],"achieved":[116],"refinements":[118],"architecture":[120],"training":[122],"6%":[124],"adding":[126],"0.8":[127],"h":[128],"in-domain":[130],"adaptation":[131]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}