{"id":"https://openalex.org/W4408353818","doi":"https://doi.org/10.1109/icassp49660.2025.10890830","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","display_name":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353818","doi":"https://doi.org/10.1109/icassp49660.2025.10890830"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890830","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/A5061783951","display_name":"Ahmed Adel Attia","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmed Adel Attia","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052171928","display_name":"Dorottya Demszky","orcid":"https://orcid.org/0000-0002-6759-9367"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dorottya Demszky","raw_affiliation_strings":["Stanford University,CA,USA"],"affiliations":[{"raw_affiliation_string":"Stanford University,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053603914","display_name":"Tol\u00fal\u1ecdpe \u00d2g\u00fanrem\u00ed","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tol\u00fal\u1ecdpe \u00d2g\u00fanrem\u00ed","raw_affiliation_strings":["Stanford University,CA,USA"],"affiliations":[{"raw_affiliation_string":"Stanford University,CA,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091253113","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0001-8802-0783"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Espy-Wilson","raw_affiliation_strings":["University of Maryland,College Park,MD,USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061783951"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":4.3637,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93378394,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"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":0.9878000020980835,"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":0.9878000020980835,"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":0.9819999933242798,"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/T11309","display_name":"Music and Audio Processing","score":0.9478999972343445,"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":0.7169797420501709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6832362413406372},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5625255107879639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3218613862991333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169797420501709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6832362413406372},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5625255107879639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3218613862991333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890830","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":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306137","display_name":"Bill and Melinda Gates Foundation","ror":"https://ror.org/0456r8d26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1597121597","https://openalex.org/W1994888226","https://openalex.org/W2094954292","https://openalex.org/W2127141656","https://openalex.org/W2963574857","https://openalex.org/W3015834770","https://openalex.org/W3035390927","https://openalex.org/W3127686677","https://openalex.org/W3198771897","https://openalex.org/W3209059054","https://openalex.org/W3213029956","https://openalex.org/W4205948992","https://openalex.org/W4221140371","https://openalex.org/W4310348293","https://openalex.org/W4311404391","https://openalex.org/W4385570127","https://openalex.org/W4385822587","https://openalex.org/W4388017424","https://openalex.org/W4390675112","https://openalex.org/W4391491233","https://openalex.org/W4392904445","https://openalex.org/W4392908601","https://openalex.org/W4392909314","https://openalex.org/W4393152829","https://openalex.org/W4404518524","https://openalex.org/W6780218876","https://openalex.org/W6861308535","https://openalex.org/W6910206221"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Creating":[0],"Automatic":[1],"Speech":[2],"Recognition":[3],"(ASR)":[4],"systems":[5],"that":[6,47,54],"are":[7],"robust":[8],"and":[9,25,56,81],"resilient":[10],"to":[11,16,22,41,77],"classroom":[12,43,82],"conditions":[13],"is":[14,49],"paramount":[15],"the":[17,32,42,58,74],"development":[18],"of":[19,34,63,68],"AI":[20],"tools":[21],"aid":[23],"teachers":[24],"students.":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"study":[31],"efficacy":[33],"continued":[35],"pretraining":[36],"(CPT)":[37],"in":[38,53],"adapting":[39],"Wav2vec2.0":[40],"domain.":[44],"We":[45],"show":[46],"CPT":[48,72],"a":[50],"powerful":[51],"tool":[52],"regard":[55],"reduces":[57],"Word":[59],"Error":[60],"Rate":[61],"(WER)":[62],"Wav2vec2.0-based":[64],"models":[65],"by":[66],"upwards":[67],"10%.":[69],"More":[70],"specifically,":[71],"improves":[73],"model\u2019s":[75],"robustness":[76],"different":[78],"noises,":[79],"microphones":[80],"conditions.":[83]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
