{"id":"https://openalex.org/W4405867986","doi":"https://doi.org/10.1145/3696409.3700259","title":"Mix-fine-tune: An Alternate Fine-tuning Strategy for Domain Adaptation and Generalization of Low-resource ASR","display_name":"Mix-fine-tune: An Alternate Fine-tuning Strategy for Domain Adaptation and Generalization of Low-resource ASR","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4405867986","doi":"https://doi.org/10.1145/3696409.3700259"},"language":"en","primary_location":{"id":"doi:10.1145/3696409.3700259","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700259","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700259?download=true","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700259?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111103714","display_name":"Chengxi Lei","orcid":"https://orcid.org/0009-0003-5799-5977"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Chengxi Lei","raw_affiliation_strings":["Massey university, Auckland, NZ"],"raw_orcid":"https://orcid.org/0009-0003-5799-5977","affiliations":[{"raw_affiliation_string":"Massey university, Auckland, NZ","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070580244","display_name":"Satwinder Singh","orcid":"https://orcid.org/0000-0001-9032-6781"},"institutions":[{"id":"https://openalex.org/I154130895","display_name":"University of Auckland","ror":"https://ror.org/03b94tp07","country_code":"NZ","type":"education","lineage":["https://openalex.org/I154130895"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Satwinder Dr Singh","raw_affiliation_strings":["University of Auckland, Auckland, NZ"],"raw_orcid":"https://orcid.org/0000-0001-9032-6781","affiliations":[{"raw_affiliation_string":"University of Auckland, Auckland, NZ","institution_ids":["https://openalex.org/I154130895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041651091","display_name":"Feng Hou","orcid":"https://orcid.org/0000-0001-5776-9177"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Feng Hou","raw_affiliation_strings":["Massey University, Auckland, NZ"],"raw_orcid":"https://orcid.org/0000-0001-5776-9177","affiliations":[{"raw_affiliation_string":"Massey University, Auckland, NZ","institution_ids":["https://openalex.org/I51158804"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022594144","display_name":"Ruili Wang","orcid":"https://orcid.org/0000-0003-2899-9816"},"institutions":[{"id":"https://openalex.org/I51158804","display_name":"Massey University","ror":"https://ror.org/052czxv31","country_code":"NZ","type":"education","lineage":["https://openalex.org/I51158804"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Ruili Wang","raw_affiliation_strings":["Massey University, Auckland, NZ"],"raw_orcid":"https://orcid.org/0000-0003-2899-9816","affiliations":[{"raw_affiliation_string":"Massey University, Auckland, NZ","institution_ids":["https://openalex.org/I51158804"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26876751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9976999759674072,"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":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9952999949455261,"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/T12676","display_name":"Machine Learning and ELM","score":0.9732999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7495498657226562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7299593091011047},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6580132842063904},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6548030972480774},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6418396830558777},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6196659207344055},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4736063480377197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22838246822357178},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11110231280326843},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08803132176399231},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05818477272987366},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.04727834463119507}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7495498657226562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7299593091011047},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6580132842063904},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6548030972480774},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6418396830558777},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6196659207344055},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4736063480377197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22838246822357178},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11110231280326843},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08803132176399231},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05818477272987366},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.04727834463119507},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696409.3700259","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700259","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700259?download=true","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696409.3700259","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700259","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700259?download=true","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405867986.pdf","grobid_xml":"https://content.openalex.org/works/W4405867986.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2029538739","https://openalex.org/W2127141656","https://openalex.org/W2566079294","https://openalex.org/W2888469011","https://openalex.org/W2916984808","https://openalex.org/W2995181338","https://openalex.org/W3163839574","https://openalex.org/W3197876970","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212799896","https://openalex.org/W3213029956","https://openalex.org/W4224933812","https://openalex.org/W4224934179","https://openalex.org/W4286685063","https://openalex.org/W4385477881","https://openalex.org/W4385799550","https://openalex.org/W4385823064","https://openalex.org/W4388017359"],"related_works":["https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"Self-supervised":[0],"Learning":[1],"(SSL)":[2],"using":[3,182],"extensive":[4],"unlabeled":[5],"speech":[6,105,201],"data":[7,31,65],"has":[8],"significantly":[9],"improved":[10],"the":[11,24,30,39,54,91,94,110,134,147,155,159,164,179,183,196,210],"performance":[12],"of":[13,26,93,103,178],"ASR":[14,37,88],"models":[15,56,197],"on":[16,199],"datasets":[17],"like":[18,203],"LibriSpeech.However,":[19],"few":[20],"studies":[21],"have":[22],"addressed":[23],"issue":[25],"domain":[27,85,165,208],"mismatch":[28,86,166],"between":[29,153,167],"used":[32,46,115,142],"to":[33,47,57,69,83,116,162,205],"pre-train":[34],"and":[35,66,90,109,158,169],"fine-tune":[36],"models.Moreover,":[38],"Empirical":[40],"Risk":[41],"Minimization":[42],"(ERM)":[43],"principle,":[44],"commonly":[45],"train":[48],"deep":[49],"learning":[50],"models,":[51],"often":[52],"causes":[53],"trained":[55],"exhibit":[58],"undesirable":[59],"behaviors":[60],"such":[61],"as":[62,107],"memorizing":[63],"training":[64,96],"being":[67],"sensitive":[68],"adversarial":[70],"examples.Thus,":[71],"in":[72,87],"this":[73],"paper,":[74],"we":[75],"propose":[76],"an":[77],"alternate":[78],"fine-tuning":[79,128,148,175],"strategy,":[80],"called":[81],"Mix-fine-tune,":[82],"address":[84,163],"systems":[89],"limitations":[92],"ERM":[95],"principle.Mix-finetune":[97],"use":[98],"a":[99,118,129,206],"data-driven":[100],"weighted":[101,119],"sum":[102],"two":[104],"sequences":[106,113],"input":[108],"corresponding":[111],"text":[112],"are":[114],"calculate":[117],"audio-text":[120],"alignment":[121],"Connectionist":[122],"Temporal":[123],"Classification":[124],"(CTC)":[125],"loss":[126,157,161],"for":[127,144],"pre-trained":[130,198],"model.Additionally,":[131],"Mix-fine-tune":[132,193],"incorporates":[133],"masked":[135],"Contrastive":[136],"Predictive":[137],"Coding":[138],"(CPC)":[139],"loss,":[140],"previously":[141],"exclusively":[143],"pre-training,":[145],"into":[146],"process.Our":[149],"novel":[150],"strategy":[151],"alternates":[152],"minimizing":[154],"CTC":[156],"CPC":[160],"pre-training":[168],"fine-tuning.We":[170],"validate":[171],"our":[172],"method":[173],"by":[174,215],"different":[176],"sizes":[177],"Wav2Vec":[180],"model":[181],"public":[184],"Air":[185],"Traffic":[186],"Control":[187],"(ATC)":[188],"corpus.The":[189],"experiments":[190],"show":[191],"that":[192],"efficiently":[194],"adapts":[195],"general":[200],"corpora":[202],"LibriSpeech":[204],"specific":[207],"(e.g.,":[209],"air":[211],"traffic":[212],"control":[213],"domain)":[214],"fine-turning.":[216]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}