{"id":"https://openalex.org/W4403783658","doi":"https://doi.org/10.48550/arxiv.2409.14494","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for\n Classroom Environments","display_name":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for\n Classroom Environments","publication_year":2024,"publication_date":"2024-09-13","ids":{"openalex":"https://openalex.org/W4403783658","doi":"https://doi.org/10.48550/arxiv.2409.14494"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14494","pdf_url":"http://arxiv.org/pdf/2409.14494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2409.14494","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061783951","display_name":"Ahmed Adel Attia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Attia, Ahmed Adel","raw_affiliation_strings":[],"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":"Demszky, Dorottya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053603914","display_name":"Tol\u00fal\u1ecdpe \u00d2g\u00fanrem\u00ed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ogunremi, Tolulope","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375073","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0002-9031-6433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jing","raw_affiliation_strings":[],"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":"Espy-Wilson, Carol","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":77},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9874,"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":0.9874,"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":0.9804,"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":0.9471,"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":[],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.59530556},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5434061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.50477064},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3204802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28615677},{"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":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14494","pdf_url":"http://arxiv.org/pdf/2409.14494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14494","pdf_url":"http://arxiv.org/pdf/2409.14494","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396701345","https://openalex.org/W4396696052","https://openalex.org/W4391913857","https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2001405890"],"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's":[75],"robustness":[76],"different":[78],"noises,":[79],"microphones":[80],"conditions.":[83]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4403783658","counts_by_year":[],"updated_date":"2025-04-16T03:58:01.003375","created_date":"2024-10-26"}