{"id":"https://openalex.org/W3163910948","doi":"https://doi.org/10.1109/icassp39728.2021.9413538","title":"A Comparison Study on Infant-Parent Voice Diarization","display_name":"A Comparison Study on Infant-Parent Voice Diarization","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163910948","doi":"https://doi.org/10.1109/icassp39728.2021.9413538","mag":"3163910948","pmid":"https://pubmed.ncbi.nlm.nih.gov/35291257"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8919348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048524258","display_name":"Junzhe Zhu","orcid":"https://orcid.org/0000-0002-4316-8570"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhe Zhu","raw_affiliation_strings":["University of Illinois,Urbana-Champaign","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["University of Illinois,Urbana-Champaign","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040993718","display_name":"Nancy L. McElwain","orcid":"https://orcid.org/0000-0001-9586-5020"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy L. McElwain","raw_affiliation_strings":["University of Illinois,Urbana-Champaign","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06302914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2021","issue":null,"first_page":"7178","last_page":"7182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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/T13289","display_name":"Infant Health and Development","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9945999979972839,"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":0.7536160945892334},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6202995777130127},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5923196077346802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5500440001487732},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5238816142082214},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5173763632774353},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5040192008018494},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.48641014099121094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4611615836620331},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43144336342811584},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.23120802640914917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08107182383537292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7536160945892334},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6202995777130127},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5923196077346802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5500440001487732},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5238816142082214},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5173763632774353},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5040192008018494},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.48641014099121094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611615836620331},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43144336342811584},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.23120802640914917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08107182383537292},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:35291257","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35291257","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8919348","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8919348","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8919348","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8919348","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306114","display_name":"U.S. Department of Agriculture","ror":"https://ror.org/01na82s61"},{"id":"https://openalex.org/F4320332299","display_name":"National Institute of Food and Agriculture","ror":"https://ror.org/05qx3fv49"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"},{"id":"https://openalex.org/F4320337347","display_name":"National Institute on Drug Abuse","ror":"https://ror.org/00fq5cm18"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1269382222","https://openalex.org/W2064675550","https://openalex.org/W2089651665","https://openalex.org/W2125642021","https://openalex.org/W2127457060","https://openalex.org/W2153372746","https://openalex.org/W2153994037","https://openalex.org/W2405472765","https://openalex.org/W2460742184","https://openalex.org/W2510733933","https://openalex.org/W2560619047","https://openalex.org/W2587126577","https://openalex.org/W2768701474","https://openalex.org/W2802905931","https://openalex.org/W2887814324","https://openalex.org/W2888800758","https://openalex.org/W2889288729","https://openalex.org/W2889496963","https://openalex.org/W2904730797","https://openalex.org/W2963351448","https://openalex.org/W2963403868","https://openalex.org/W2963452667","https://openalex.org/W2964052309","https://openalex.org/W2972449503","https://openalex.org/W2973193289","https://openalex.org/W2989863749","https://openalex.org/W3008357631","https://openalex.org/W3031133340","https://openalex.org/W4385245566","https://openalex.org/W6628383420","https://openalex.org/W6682965620","https://openalex.org/W6739901393","https://openalex.org/W6751512325","https://openalex.org/W7073832357"],"related_works":["https://openalex.org/W4389272081","https://openalex.org/W135211875","https://openalex.org/W2052269122","https://openalex.org/W4307477668","https://openalex.org/W89843531","https://openalex.org/W2398046462","https://openalex.org/W2945706271","https://openalex.org/W4387435415","https://openalex.org/W2114169842","https://openalex.org/W2535808783"],"abstract_inverted_index":{"We":[0,35,58,80,100],"design":[1],"a":[2,24,28,33,61],"framework":[3],"for":[4],"studying":[5],"prelinguistic":[6],"child":[7],"voice":[8],"from":[9],"3":[10],"to":[11,53,68,93],"24":[12],"months":[13],"based":[14],"on":[15,72,89],"state-of-the-art":[16],"algorithms":[17],"in":[18],"diarization.":[19,118],"Our":[20],"system":[21,85],"consists":[22],"of":[23,39,44,109,116],"time-invariant":[25],"feature":[26,106],"extractor,":[27],"context-dependent":[29],"embedding":[30],"generator,":[31],"and":[32],"classifier.":[34],"study":[36],"the":[37,45,55,114],"effect":[38],"swapping":[40],"out":[41],"different":[42],"components":[43],"system,":[46],"as":[47,49],"well":[48],"changing":[50],"loss":[51],"function,":[52],"find":[54],"best":[56,84],"performance.":[57],"also":[59,101],"present":[60],"multiple-instance":[62],"learning":[63],"technique":[64],"that":[65,82,103],"allows":[66],"us":[67],"pre-train":[69],"our":[70,83],"parameters":[71],"larger":[73],"datasets":[74],"with":[75],"coarser":[76],"segment":[77],"boundary":[78],"labels.":[79],"found":[81,102],"achieved":[86,96],"43.8%":[87],"DER":[88,95],"test":[90],"dataset,":[91],"compared":[92],"55.4%":[94],"by":[97],"LENA":[98],"software.":[99],"using":[104],"convolutional":[105],"extractor":[107],"instead":[108],"logmel":[110],"features":[111],"significantly":[112],"increases":[113],"performance":[115],"neural":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}