{"id":"https://openalex.org/W4415432670","doi":"https://doi.org/10.21437/interspeech.2025-2601","title":"Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering","display_name":"Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432670","doi":"https://doi.org/10.21437/interspeech.2025-2601"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-2601","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2601","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/2506.04981","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":"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/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/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":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/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/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/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/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":"https://openalex.org/A5063173682","display_name":"Saurabh Vyas","orcid":"https://orcid.org/0000-0002-5406-3272"},"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/A5114060825","display_name":"Andreas Stolcke","orcid":null},"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":0.13943105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3618","last_page":"3622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9046000242233276,"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/T12676","display_name":"Machine Learning and ELM","score":0.9046000242233276,"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/pipeline","display_name":"Pipeline (software)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.566100001335144},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.564300000667572},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5267000198364258},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4092000126838684},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.40470001101493835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422999739646912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.629800021648407},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.564300000667572},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45910000801086426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3001999855041504},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2703000009059906}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-2601","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2601","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:2506.04981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04981","pdf_url":"https://arxiv.org/pdf/2506.04981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/255777","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255777","pdf_url":"https://infoscience.epfl.ch/bitstreams/e339d289-a5c8-4b5f-99a2-a02cfa3f1ec3/download","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.04981","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04981","pdf_url":"https://arxiv.org/pdf/2506.04981","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415432670.pdf","grobid_xml":"https://content.openalex.org/works/W4415432670.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"pretrained":[1],"ASR":[2],"models":[3],"for":[4],"specific":[5],"domains":[6,22],"is":[7,12,70,126],"challenging":[8],"when":[9],"labeled":[10,18,39],"data":[11,19],"scarce.":[13],"But":[14],"unlabeled":[15],"audio":[16],"and":[17,41,75,94,115],"from":[20,45],"related":[21,48],"are":[23],"often":[24],"available.":[25],"We":[26],"propose":[27],"an":[28,42],"incremental":[29],"semi-supervised":[30],"learning":[31],"pipeline":[32],"that":[33],"first":[34],"integrates":[35],"a":[36,46,51,134],"small":[37],"in-domain":[38],"set":[40],"auxiliary":[43,58],"dataset":[44],"closely":[47],"domain,":[49],"achieving":[50],"relative":[52,111],"improvement":[53,112],"of":[54],"4%":[55],"over":[56,119],"no":[57],"data.":[59],"Filtering":[60],"based":[61],"on":[62,88,113,117],"multi-model":[63],"consensus":[64],"or":[65],"named":[66],"entity":[67],"recognition":[68],"(NER)":[69],"then":[71],"applied":[72],"to":[73,84,109],"select":[74],"iteratively":[76],"refine":[77],"pseudo-labels,":[78],"showing":[79],"slower":[80],"performance":[81,132],"saturation":[82],"compared":[83],"random":[85,123],"selection.":[86,124],"Evaluated":[87],"the":[89,127],"multi-domain":[90],"Wow":[91,114],"call":[92],"center":[93],"Fisher":[95,118],"English":[96],"corpora,":[97],"it":[98],"outperforms":[99,104],"single-step":[100,120],"fine-tuning.":[101],"Consensus-based":[102],"filtering":[103],"other":[105],"methods,":[106],"providing":[107,130],"up":[108],"22.3%":[110],"24.8%":[116],"fine-tuning":[121],"with":[122],"NER":[125],"second-best":[128],"filter,":[129],"competitive":[131],"at":[133],"lower":[135],"computational":[136],"cost.":[137]},"counts_by_year":[],"updated_date":"2026-06-21T07:57:09.225873","created_date":"2025-10-23T00:00:00"}