{"id":"https://openalex.org/W4408356223","doi":"https://doi.org/10.1109/icassp49660.2025.10888138","title":"Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering","display_name":"Speech Data Selection for Efficient ASR Fine-Tuning using Domain Classifier and Pseudo-Label Filtering","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356223","doi":"https://doi.org/10.1109/icassp49660.2025.10888138"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5108143392","display_name":"Pradeep Rangappa","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Pradeep Rangappa","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078502662","display_name":"Juan Zuluaga-G\u00f3mez","orcid":"https://orcid.org/0000-0002-6947-2706"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Juan Zuluaga-Gomez","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000784556","display_name":"Andr\u00e9s Carofilis","orcid":"https://orcid.org/0000-0001-9446-0152"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andres Carofilis","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jeena Prakash","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeena Prakash","raw_affiliation_strings":["Uniphore Software Systems,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034706108","display_name":"Sergio Burdisso","orcid":"https://orcid.org/0000-0002-7694-6834"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sergio Burdisso","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107893868","display_name":"Shashi Kumar","orcid":"https://orcid.org/0000-0002-2442-7143"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shashi Kumar","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075765823","display_name":"Esa\u00fa Villatoro-Tello","orcid":"https://orcid.org/0000-0002-1322-0358"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Esa\u00fa Villatoro-Tello","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021226188","display_name":"Iuliia Nigmatulina","orcid":"https://orcid.org/0000-0002-5111-1873"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Iuliia Nigmatulina","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114245170","display_name":"Karthik Pandia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karthik Pandia","raw_affiliation_strings":["Uniphore Software Systems,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems,India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083410051","display_name":"Aravind Ganapathiraju","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aravind Ganapathiraju","raw_affiliation_strings":["Uniphore Software Systems,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems,India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94739875,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"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":0.984499990940094,"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":0.984499990940094,"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":0.9337999820709229,"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":0.7905521392822266},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6684963703155518},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6522388458251953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5744749903678894},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5206598043441772},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.5073804259300232},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4685441255569458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905521392822266},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6684963703155518},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6522388458251953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5744749903678894},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5206598043441772},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.5073804259300232},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4685441255569458},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1489048302","https://openalex.org/W2012190582","https://openalex.org/W2022431145","https://openalex.org/W2127141656","https://openalex.org/W2132991150","https://openalex.org/W2144499799","https://openalex.org/W2147590749","https://openalex.org/W2726599793","https://openalex.org/W2973094925","https://openalex.org/W3015237657","https://openalex.org/W3097777922","https://openalex.org/W3162334527","https://openalex.org/W3189209532","https://openalex.org/W3198429080","https://openalex.org/W3208887030","https://openalex.org/W3209976096","https://openalex.org/W3214456683","https://openalex.org/W4283700324","https://openalex.org/W4319862480","https://openalex.org/W4385245566","https://openalex.org/W4385799550","https://openalex.org/W4385822293","https://openalex.org/W4385822356","https://openalex.org/W4385822820","https://openalex.org/W4386025763","https://openalex.org/W4391833135","https://openalex.org/W4392904733","https://openalex.org/W4406087185","https://openalex.org/W6631190155","https://openalex.org/W6810259195","https://openalex.org/W6845587207","https://openalex.org/W6847363464","https://openalex.org/W6852909395","https://openalex.org/W6857062747"],"related_works":["https://openalex.org/W4390306690","https://openalex.org/W1969209172","https://openalex.org/W4205762803","https://openalex.org/W4385572141","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W4281997472"],"abstract_inverted_index":{"In":[0,47],"real-world":[1],"speech":[2,15],"data":[3,9,16,28,70,103],"processing,":[4],"the":[5,11,72,107,120],"scarcity":[6],"of":[7,13],"annotated":[8],"and":[10,41,62,83,99],"abundance":[12],"unlabelled":[14],"present":[17],"a":[18,52,58,76],"significant":[19],"challenge.":[20],"To":[21],"address":[22],"this,":[23],"we":[24,50,68],"propose":[25,51],"an":[26],"efficient":[27,43],"selection":[29,104,126],"pipeline":[30,40,105],"for":[31,45,93],"fine-tuning":[32,94],"ASR":[33],"models":[34,98],"by":[35,110],"generating":[36],"pseudo-labels":[37],"using":[38,75],"WhisperX":[39],"selecting":[42],"labels":[44,89],"fine-tuning.":[46],"our":[48],"work,":[49],"domain":[53],"classifier":[54,73],"system":[55],"developed":[56],"with":[57],"computationally":[59],"inexpensive":[60],"TFIDF":[61],"classical":[63],"machine":[64],"learning":[65],"algorithm.":[66],"Later,":[67],"filter":[69],"from":[71],"output":[74],"novel":[77],"metric":[78],"that":[79],"assesses":[80],"word":[81],"ratio":[82],"perplexity":[84],"distribution.":[85],"The":[86],"filtered":[87],"pseudo":[88],"are":[90],"then":[91],"used":[92],"standard":[95],"encoder-decoder":[96],"Whisper":[97],"Zipformer.":[100],"Our":[101],"proposed":[102],"reduces":[106],"dataset":[108],"size":[109],"approximately":[111],"1/100<sup":[112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">th</sup>":[114],"while":[115],"maintaining":[116],"performance":[117],"comparable":[118],"to":[119],"full":[121],"dataset,":[122],"outperforming":[123],"random":[124],"domain-independent":[125],"strategies.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
