{"id":"https://openalex.org/W4415432690","doi":"https://doi.org/10.21437/interspeech.2025-2580","title":"Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering","display_name":"Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432690","doi":"https://doi.org/10.21437/interspeech.2025-2580"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.03681","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108143392","display_name":"Pradeep Rangappa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pradeep Rangappa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000784556","display_name":"Andr\u00e9s Carofilis","orcid":"https://orcid.org/0000-0001-9446-0152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9s Carofilis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107893868","display_name":"Shashi Kumar","orcid":"https://orcid.org/0000-0002-2442-7143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shashi Kumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034706108","display_name":"Sergio Burdisso","orcid":"https://orcid.org/0000-0002-7694-6834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergio Burdisso","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084521938","display_name":"Srikanth Madikeri","orcid":"https://orcid.org/0000-0002-4361-784X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srikanth Madikeri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075765823","display_name":"Esa\u00fa Villatoro-Tello","orcid":"https://orcid.org/0000-0002-1322-0358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esa\u00fa Villatoro-Tello","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067433878","display_name":"Bidisha Sharma","orcid":"https://orcid.org/0000-0002-4195-3532"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bidisha Sharma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petr Motlicek","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004977752","display_name":"Kadri Hac\u0131o\u011flu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kadri Hacioglu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020547781","display_name":"Shankar M. Venkatesan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shankar Venkatesan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Saurabh Vyas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabh Vyas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":13,"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":0.32693376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4928","last_page":"4932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8413000106811523,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8413000106811523,"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/T12676","display_name":"Machine Learning and ELM","score":0.8374999761581421,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.8245000243186951,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6057000160217285},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5475999712944031},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5041000247001648},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4542999863624573},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.3833000063896179},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.38269999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016999959945679},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6057000160217285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5709999799728394},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5153999924659729},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3822999894618988},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3698999881744385},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34279999136924744},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.26159998774528503},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-2580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.03681","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03681","pdf_url":"https://arxiv.org/pdf/2506.03681","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.03681","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03681","pdf_url":"https://arxiv.org/pdf/2506.03681","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415432690.pdf","grobid_xml":"https://content.openalex.org/works/W4415432690.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0,100],"pretrained":[1],"ASR":[2,33,98],"models":[3],"for":[4,9],"specific":[5],"domains":[6],"is":[7,128],"challenging":[8],"small":[10],"organizations":[11],"with":[12,122],"limited":[13],"labeled":[14],"data":[15,23,108],"and":[16,26,42,63,81],"computational":[17],"resources.":[18],"Here,":[19],"we":[20],"explore":[21],"different":[22],"selection":[24,50],"pipelines":[25],"propose":[27],"a":[28,84,90,125],"robust":[29],"approach":[30,47,92],"that":[31],"improves":[32],"adaptation":[34],"by":[35],"filtering":[36,114],"pseudo-labels":[37],"generated":[38],"using":[39,83],"Whisper":[40,80],"(encoder-decoder)":[41],"Zipformer":[43,82],"(transducer)":[44],"models.":[45],"Our":[46],"integrates":[48],"multiple":[49],"strategies":[51],"--":[52,69],"including":[53],"word":[54],"error":[55,65],"rate":[56,66],"(WER)":[57],"prediction,":[58],"named":[59],"entity":[60],"recognition":[61],"(NER),":[62],"character":[64],"(CER)":[67],"analysis":[68],"to":[70,89,118],"extract":[71],"high-quality":[72],"training":[73],"segments.":[74],"We":[75],"evaluate":[76],"our":[77,113],"method":[78],"on":[79,94,101,130],"7500-hour":[85],"baseline,":[86],"comparing":[87],"it":[88],"CER-based":[91],"relying":[93],"hypotheses":[95],"from":[96],"three":[97],"systems.":[99],"7500":[102],"hours":[103,120],"of":[104],"pseudo-labeled":[105],"call":[106],"center":[107],"achieves":[109],"12.3%":[110],"WER,":[111],"while":[112],"reduces":[115],"the":[116],"dataset":[117],"100":[119],"(1.4%)":[121],"similar":[123,126],"performance;":[124],"trend":[127],"observed":[129],"Fisher":[131],"English.":[132]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-23T00:00:00"}