{"id":"https://openalex.org/W4415433319","doi":"https://doi.org/10.21437/interspeech.2025-1432","title":"From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data","display_name":"From Weak Labels to Strong Results: Utilizing 5,000 Hours of Noisy Classroom Transcripts with Minimal Accurate Data","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433319","doi":"https://doi.org/10.21437/interspeech.2025-1432"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1432","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/2505.17088","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061033321","display_name":"Ahmed Attia","orcid":"https://orcid.org/0000-0002-6751-6584"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ahmed Attia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052171928","display_name":"Dorottya Demszky","orcid":"https://orcid.org/0000-0002-6759-9367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dorottya Demszky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038517767","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-9918-8642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carol Espy-Wilson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061033321"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23091817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3678","last_page":"3682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.7605999708175659,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.7605999708175659,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12884","display_name":"Educational Assessment and Pedagogy","score":0.6958000063896179,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.6693000197410583,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.59170001745224},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5424000024795532},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5224999785423279},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48820000886917114},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4223000109195709},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3091000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6319000124931335},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6244000196456909},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5424000024795532},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5128999948501587},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4223000109195709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3070000112056732},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2720000147819519}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-1432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1432","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:2505.17088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.17088","pdf_url":"https://arxiv.org/pdf/2505.17088","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2505.17088","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"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":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.17088","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.17088","pdf_url":"https://arxiv.org/pdf/2505.17088","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,95,131],"speech":[3,76],"recognition":[4],"has":[5],"relied":[6],"on":[7,10,92,102,108],"models":[8,88],"trained":[9],"vast":[11],"amounts":[12],"of":[13,26,36],"labeled":[14],"data.":[15,39,104],"However,":[16],"classroom":[17,75],"Automatic":[18],"Speech":[19],"Recognition":[20],"(ASR)":[21],"faces":[22],"the":[23,57,72],"real-world":[24,132],"challenge":[25],"abundant":[27,61],"weak":[28,63,93,113],"transcripts":[29,64,94],"paired":[30],"with":[31,66],"only":[32],"a":[33,84,96],"small":[34],"amount":[35],"accurate,":[37],"gold-standard":[38,68],"In":[40],"such":[41],"low-resource":[42,129],"settings,":[43],"high":[44],"transcription":[45],"costs":[46],"make":[47],"re-transcription":[48],"impractical.":[49],"To":[50],"address":[51],"this,":[52],"we":[53],"ask:":[54],"what":[55],"is":[56,71],"best":[58],"approach":[59],"when":[60],"inexpensive":[62],"coexist":[65],"limited":[67],"data,":[69],"as":[70,123],"case":[73],"for":[74,128],"data?":[77],"We":[78],"propose":[79],"Weakly":[80],"Supervised":[81],"Pretraining":[82],"(WSP),":[83],"two-step":[85],"process":[86],"where":[87],"are":[89],"first":[90],"pretrained":[91],"supervised":[97],"manner,":[98],"and":[99,111],"then":[100],"fine-tuned":[101],"accurate":[103],"Our":[105],"results,":[106],"based":[107],"both":[109],"synthetic":[110],"real":[112],"transcripts,":[114],"show":[115],"that":[116],"WSP":[117],"outperforms":[118],"alternative":[119],"methods,":[120],"establishing":[121],"it":[122],"an":[124],"effective":[125],"training":[126],"methodology":[127],"ASR":[130],"scenarios.":[133]},"counts_by_year":[],"updated_date":"2026-06-09T15:46:55.921056","created_date":"2025-10-24T00:00:00"}