{"id":"https://openalex.org/W2981983183","doi":"https://doi.org/10.1109/icassp40776.2020.9053251","title":"Meta-Learning for Robust Child-Adult Classification from Speech","display_name":"Meta-Learning for Robust Child-Adult Classification from Speech","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981983183","doi":"https://doi.org/10.1109/icassp40776.2020.9053251","mag":"2981983183"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040007143","display_name":"Nithin Rao Koluguri","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nithin Rao Koluguri","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849944","display_name":"Manoj Kumar","orcid":"https://orcid.org/0000-0003-2100-461X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689634","display_name":"So Hyun Kim","orcid":"https://orcid.org/0000-0003-4269-0866"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"id":"https://openalex.org/I94690351","display_name":"Center for Autism and Related Disorders","ror":"https://ror.org/00t7r5h51","country_code":"US","type":"other","lineage":["https://openalex.org/I94690351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"So Hyun Kim","raw_affiliation_strings":["Center for Autism and the Developing Brain, Weill Cornell Medicine","Weill Cornell Medicine,Center for Autism and the Developing Brain"],"affiliations":[{"raw_affiliation_string":"Center for Autism and the Developing Brain, Weill Cornell Medicine","institution_ids":["https://openalex.org/I94690351","https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Weill Cornell Medicine,Center for Autism and the Developing Brain","institution_ids":["https://openalex.org/I94690351","https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082294410","display_name":"Catherine Lord","orcid":"https://orcid.org/0000-0001-5633-1253"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Lord","raw_affiliation_strings":["Semel Institute of Neuroscience and Human behavior, University of California, Los Angeles","University of California,Semel Institute of Neuroscience and Human Behavior,Los Angeles"],"affiliations":[{"raw_affiliation_string":"Semel Institute of Neuroscience and Human behavior, University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California,Semel Institute of Neuroscience and Human Behavior,Los Angeles","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040007143"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.1372,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51993426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.802861213684082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.609298050403595},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5964450836181641},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5392113924026489},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5255200862884521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5200455188751221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5040527582168579},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4995608329772949},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4949900507926941},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4778939485549927},{"id":"https://openalex.org/keywords/autism","display_name":"Autism","score":0.4683969020843506},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.464652955532074},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4625268578529358},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4252271354198456},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2756582498550415},{"id":"https://openalex.org/keywords/developmental-psychology","display_name":"Developmental psychology","score":0.15005120635032654}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.802861213684082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.609298050403595},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5964450836181641},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5392113924026489},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5255200862884521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5200455188751221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5040527582168579},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4995608329772949},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4949900507926941},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4778939485549927},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.4683969020843506},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.464652955532074},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4625268578529358},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4252271354198456},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2756582498550415},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.15005120635032654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11400","pdf_url":"https://arxiv.org/pdf/1910.11400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2981983183","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1910.11400.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.11400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.11400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11400","pdf_url":"https://arxiv.org/pdf/1910.11400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981983183.pdf","grobid_xml":"https://content.openalex.org/works/W2981983183.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1994888226","https://openalex.org/W1995422333","https://openalex.org/W2109761419","https://openalex.org/W2144446993","https://openalex.org/W2330594182","https://openalex.org/W2339747551","https://openalex.org/W2515622192","https://openalex.org/W2534843682","https://openalex.org/W2587126577","https://openalex.org/W2601450892","https://openalex.org/W2614349964","https://openalex.org/W2638067502","https://openalex.org/W2802905931","https://openalex.org/W2889288729","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2903158431","https://openalex.org/W2944777581","https://openalex.org/W2963386851","https://openalex.org/W2963702081","https://openalex.org/W2964316912","https://openalex.org/W2973193289","https://openalex.org/W3007928779","https://openalex.org/W3091905774","https://openalex.org/W6735236233","https://openalex.org/W6736057607","https://openalex.org/W6751191447","https://openalex.org/W6756615331","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2887584715","https://openalex.org/W3151507536","https://openalex.org/W2904913586","https://openalex.org/W3015141382","https://openalex.org/W3183472812","https://openalex.org/W3015299720","https://openalex.org/W3086441688","https://openalex.org/W3162133897","https://openalex.org/W3210277894","https://openalex.org/W3149926570","https://openalex.org/W3209773571","https://openalex.org/W3111112601","https://openalex.org/W2408690103","https://openalex.org/W3015672537","https://openalex.org/W3015817524","https://openalex.org/W3185249749","https://openalex.org/W3086923691","https://openalex.org/W3045669268","https://openalex.org/W2805251476","https://openalex.org/W2963891433"],"abstract_inverted_index":{"Computational":[0],"modeling":[1,99],"of":[2,37,84],"naturalistic":[3],"conversations":[4,47],"in":[5,12,44,68,86,103,144,152],"clinical":[6],"applications":[7],"has":[8],"seen":[9],"growing":[10],"interest":[11],"the":[13,23,69,74,82,104],"past":[14],"decade.":[15],"An":[16],"important":[17],"use-case":[18],"involves":[19],"child-adult":[20,41,101,167],"interactions":[21],"within":[22,71],"autism":[24],"diagnosis":[25],"and":[26,59,73,146],"intervention":[27],"domain.":[28],"In":[29,77],"this":[30,78],"paper,":[31],"we":[32,80,113],"address":[33],"a":[34,52,92,108,115],"specific":[35],"sub-problem":[36],"speaker":[38,42,53,58,130,164],"diarization,":[39],"namely":[40],"classification":[43,54,139,168],"such":[45],"dyadic":[46],"with":[48,117],"specified":[49],"roles.":[50],"Training":[51],"system":[55],"robust":[56,163],"to":[57,65,121],"channel":[60],"conditions":[61],"is":[62],"challenging":[63],"due":[64],"inherent":[66],"variability":[67],"speech":[70],"children":[72],"adult":[75],"interlocutors.":[76],"work,":[79],"propose":[81],"use":[83],"meta-learning,":[85],"particular":[87],"prototypical":[88],"networks":[89],"which":[90],"optimize":[91],"metric":[93],"space":[94],"across":[95],"multiple":[96],"tasks.":[97],"By":[98],"every":[100],"pair":[102],"training":[105],"set":[106],"as":[107],"separate":[109],"task":[110],"during":[111],"meta-training,":[112],"learn":[114],"representation":[116],"improved":[118],"generalizability":[119],"compared":[120],"conventional":[122],"supervised":[123,138],"learning.":[124],"We":[125],"demonstrate":[126],"improvements":[127],"over":[128],"state-of-the-art":[129],"embeddings":[131,165],"(x-vectors)":[132],"under":[133],"two":[134],"evaluation":[135],"settings:":[136],"weakly":[137],"(upto":[140,148],"14.53%":[141],"relative":[142,149],"improvement":[143,151],"F1-scores)":[145],"clustering":[147],"9.66%":[150],"cluster":[153],"purity).":[154],"Our":[155],"results":[156],"show":[157],"that":[158],"protonets":[159],"can":[160],"potentially":[161],"extract":[162],"for":[166],"from":[169],"speech.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}