{"id":"https://openalex.org/W4415014512","doi":"https://doi.org/10.21437/interspeech.2025-1002","title":"FT-Boosted SV: Towards Noise Robust Speaker Verification for English Speaking Classroom Environments","display_name":"FT-Boosted SV: Towards Noise Robust Speaker Verification for English Speaking Classroom Environments","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415014512","doi":"https://doi.org/10.21437/interspeech.2025-1002"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1002","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1002","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/2505.20222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120086316","display_name":"Saba Tabatabaee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Saba Tabatabaee","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":"Jing Liu","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":"Carol Espy-Wilson","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120086316"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4121,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91525293,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2815","last_page":"2819"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.9961000084877014,"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":0.9950000047683716,"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":0.9932000041007996,"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/baseline","display_name":"Baseline (sea)","score":0.6295999884605408},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5551000237464905},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5411999821662903},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4837000072002411},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.41029998660087585},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.34450000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592999935150146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.644599974155426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6295999884605408},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5551000237464905},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5411999821662903},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4837000072002411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45890000462532043},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.41029998660087585},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3319999873638153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1002","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1002","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:2505.20222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20222","pdf_url":"https://arxiv.org/pdf/2505.20222","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:2505.20222","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.20222","pdf_url":"https://arxiv.org/pdf/2505.20222","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/W4415014512.pdf","grobid_xml":"https://content.openalex.org/works/W4415014512.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Creating":[0],"Speaker":[1],"Verification":[2],"(SV)":[3],"systems":[4],"for":[5,20,77,102,123],"classroom":[6,12,50,79],"settings":[7],"that":[8,26,54,63],"are":[9],"robust":[10],"to":[11,43,49,109,130],"noises":[13],"such":[14],"as":[15],"babble":[16],"noise":[17],"is":[18,60],"crucial":[19],"the":[21,35,45,67,91,105,110,126],"development":[22],"of":[23,37,72,90],"AI":[24],"tools":[25],"assist":[27],"educational":[28],"environments.":[29,51],"In":[30],"this":[31,86],"work,":[32],"we":[33],"study":[34],"efficacy":[36],"finetuning":[38,55],"with":[39,56],"augmented":[40,57],"children":[41,82],"datasets":[42,59,80],"adapt":[44],"x-vector":[46,73,115],"and":[47,65,74,81],"ECAPA-TDNN":[48,75,92,111],"We":[52],"demonstrate":[53],"children's":[58],"powerful":[61],"in":[62,104,125],"regard":[64],"reduces":[66,88],"Equal":[68],"Error":[69],"Rate":[70],"(EER)":[71],"models":[76],"both":[78],"speech":[83],"datasets.":[84],"Notably,":[85],"method":[87],"EER":[89],"model":[93,116],"on":[94],"average":[95,121],"by":[96],"half":[97],"(a":[98],"5":[99],"%":[100,120],"improvement)":[101],"classrooms":[103,124],"MPT":[106],"dataset":[107,128],"compared":[108,129],"baseline":[112],"model.":[113],"The":[114],"shows":[117],"an":[118],"8":[119],"improvement":[122],"NCTE":[127],"its":[131],"baseline.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}