{"id":"https://openalex.org/W4319862457","doi":"https://doi.org/10.1109/slt54892.2023.10023121","title":"A Zero-Shot Approach to Identifying Children's Speech in Automatic Gender Classification","display_name":"A Zero-Shot Approach to Identifying Children's Speech in Automatic Gender Classification","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862457","doi":"https://doi.org/10.1109/slt54892.2023.10023121"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023121","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023121","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058360765","display_name":"Amruta Saraf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amruta Saraf","raw_affiliation_strings":["Pindrop,Atlanta,USA","Pindrop, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pindrop,Atlanta,USA","institution_ids":[]},{"raw_affiliation_string":"Pindrop, Atlanta, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082619376","display_name":"Ganesh Sivaraman","orcid":"https://orcid.org/0000-0002-5705-4443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ganesh Sivaraman","raw_affiliation_strings":["Pindrop,Atlanta,USA","Pindrop, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pindrop,Atlanta,USA","institution_ids":[]},{"raw_affiliation_string":"Pindrop, Atlanta, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010032071","display_name":"Elie Khoury","orcid":"https://orcid.org/0000-0001-9568-3729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elie Khoury","raw_affiliation_strings":["Pindrop,Atlanta,USA","Pindrop, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pindrop,Atlanta,USA","institution_ids":[]},{"raw_affiliation_string":"Pindrop, Atlanta, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54376313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"853","last_page":"859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9994000196456909,"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/speech-recognition","display_name":"Speech recognition","score":0.7026368379592896},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6639153957366943},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6587151288986206},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5693764090538025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.568810224533081},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5635824799537659},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45253145694732666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4360072910785675},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.43295711278915405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38804471492767334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3247787058353424}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7026368379592896},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6639153957366943},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6587151288986206},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5693764090538025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.568810224533081},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5635824799537659},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45253145694732666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4360072910785675},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.43295711278915405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38804471492767334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3247787058353424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023121","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023121","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4300000071525574},{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W168931615","https://openalex.org/W1494198834","https://openalex.org/W1833248789","https://openalex.org/W1994888226","https://openalex.org/W1996601463","https://openalex.org/W2091425152","https://openalex.org/W2116516955","https://openalex.org/W2135731872","https://openalex.org/W2137075158","https://openalex.org/W2145528340","https://openalex.org/W2191779130","https://openalex.org/W2407342760","https://openalex.org/W2492342376","https://openalex.org/W2808631503","https://openalex.org/W2962898354","https://openalex.org/W3006898571","https://openalex.org/W3015337773","https://openalex.org/W3095057960","https://openalex.org/W3141174088","https://openalex.org/W3160812582","https://openalex.org/W3181310845","https://openalex.org/W4206713267","https://openalex.org/W4297841705","https://openalex.org/W6675409298","https://openalex.org/W6713804741"],"related_works":["https://openalex.org/W1670332068","https://openalex.org/W2095618524","https://openalex.org/W249497648","https://openalex.org/W2347413598","https://openalex.org/W1918542373","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2350336482","https://openalex.org/W2154472250","https://openalex.org/W2229352698"],"abstract_inverted_index":{"Detecting":[0],"whether":[1],"a":[2,13,63,111,126],"speech":[3,34,41,51,101],"utterance":[4],"belongs":[5],"to":[6,26,43,49,57,67,74,97,125],"an":[7],"adult":[8,10,80],"male,":[9],"female":[11],"or":[12],"child":[14,138],"category,":[15],"also":[16],"known":[17],"as":[18,84,119],"male-female-child":[19],"(MFC)":[20],"classification":[21,105,139],"is":[22,47],"particularly":[23],"challenging":[24],"due":[25,42,56],"two":[27],"main":[28],"reasons":[29],"-":[30],"paucity":[31],"of":[32],"children's":[33,40,54],"data,":[35],"and":[36,91],"high":[37],"variability":[38],"in":[39],"developmental":[44],"changes.":[45],"It":[46],"difficult":[48],"obtain":[50],"datasets":[52],"with":[53],"voices":[55,78],"privacy":[58],"reasons.":[59],"This":[60],"paper":[61],"explores":[62],"zero-shot":[64],"learning":[65],"approach":[66],"MFC":[68,104,122,131],"classification.":[69,123],"Different":[70],"algorithms":[71],"are":[72,95,117],"explored":[73],"create":[75,98],"artificial":[76],"childlike":[77,100],"from":[79,110],"voices.":[81],"Methods":[82],"such":[83],"pitch":[85,127],"shifting,":[86],"Vocal":[87],"Tract":[88],"Length":[89],"Perturbation,":[90],"Segmental":[92],"Warping":[93],"Perturbation":[94],"used":[96,118],"synthetic":[99],"for":[102,121],"the":[103,133,137],"task.":[106],"Speaker":[107],"embeddings":[108],"extracted":[109],"DNN":[112],"based":[113,129],"speaker":[114],"recognition":[115],"system":[116],"features":[120],"Compared":[124],"frequency":[128],"baseline":[130],"classifier,":[132],"proposed":[134],"method":[135],"improves":[136],"accuracy":[140],"by":[141],"47%.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}