{"id":"https://openalex.org/W3116922522","doi":"https://doi.org/10.1145/3395035.3425182","title":"Combining Clustering and Functionals based Acoustic Feature Representations for Classification of Baby Sounds","display_name":"Combining Clustering and Functionals based Acoustic Feature Representations for Classification of Baby Sounds","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3116922522","doi":"https://doi.org/10.1145/3395035.3425182","mag":"3116922522"},"language":"en","primary_location":{"id":"doi:10.1145/3395035.3425182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425182","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"article","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/A5050585145","display_name":"Heysem Kaya","orcid":"https://orcid.org/0000-0001-7947-5508"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Heysem Kaya","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013838199","display_name":"Oxana Verkholyak","orcid":"https://orcid.org/0000-0002-5583-0410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oxana Verkholyak","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed"],"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050029665","display_name":"Maxim Markitantov","orcid":"https://orcid.org/0000-0001-7987-1025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maxim Markitantov","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed"],"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":["St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed"],"affiliations":[{"raw_affiliation_string":"St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences, St. Petersburg, Russian Fed","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050585145"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":0.5035,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64856712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","issue":null,"first_page":"509","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7566300630569458},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6530294418334961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5706271529197693},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5582159757614136},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5147507190704346},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5121557712554932},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5085855722427368},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5014779567718506},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.47876420617103577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.466891884803772},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4487895667552948},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.43792256712913513},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4195348620414734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41627633571624756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07884877920150757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566300630569458},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6530294418334961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706271529197693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5582159757614136},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5147507190704346},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5121557712554932},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5085855722427368},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5014779567718506},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.47876420617103577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.466891884803772},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4487895667552948},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.43792256712913513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4195348620414734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41627633571624756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07884877920150757},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3395035.3425182","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425182","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/415585","is_oa":false,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/415585","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Contribution to conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W88923019","https://openalex.org/W1426841925","https://openalex.org/W2026131661","https://openalex.org/W2078622091","https://openalex.org/W2090777335","https://openalex.org/W2108946139","https://openalex.org/W2134603844","https://openalex.org/W2147238549","https://openalex.org/W2186450909","https://openalex.org/W2406311945","https://openalex.org/W2407349954","https://openalex.org/W2517415851","https://openalex.org/W2625397849","https://openalex.org/W2747883328","https://openalex.org/W2749046237","https://openalex.org/W2909158286","https://openalex.org/W2963194800","https://openalex.org/W2972393344","https://openalex.org/W2972850640","https://openalex.org/W2990586529","https://openalex.org/W6944408911","https://openalex.org/W6945130725","https://openalex.org/W6964162247"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W3108667266","https://openalex.org/W2376619307","https://openalex.org/W4327524435","https://openalex.org/W4375869336"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"different":[3,55],"fusion":[4,63],"strategies":[5],"as":[6,8,31,43,45],"well":[7,44],"provides":[9],"insights":[10],"on":[11,54,72],"their":[12],"effectiveness":[13],"alongside":[14],"standalone":[15],"classifiers":[16],"in":[17],"the":[18,65,94,105,119],"framework":[19,69],"of":[20,23,28,64,82],"paralinguistic":[21],"analysis":[22],"infant":[24,85],"vocalizations.":[25],"The":[26,67],"combinations":[27],"such":[29],"systems":[30,53],"Support":[32],"Vector":[33],"Machines":[34,39],"(SVM)":[35],"and":[36,59,113],"Extreme":[37],"Learning":[38],"(ELM)":[40],"based":[41],"classifiers,":[42],"its":[46],"weighted":[47,61],"kernel":[48],"version":[49],"are":[50],"explored,":[51],"training":[52],"acoustic":[56],"feature":[57],"representations":[58],"implementing":[60],"score-level":[62],"predictions.":[66],"proposed":[68],"is":[70,79],"tested":[71],"INTERSPEECH":[73],"ComParE-2019":[74],"Baby":[75],"Sounds":[76],"corpus,":[77],"which":[78],"a":[80,98,115],"collection":[81],"Home":[83],"Bank":[84],"vocalization":[86],"corpora":[87],"annotated":[88],"for":[89],"five":[90],"classes.":[91],"Adhering":[92],"to":[93,118],"challenge":[95,106],"protocol,":[96],"using":[97],"single":[99],"test":[100],"set":[101],"submission":[102],"we":[103],"outperform":[104],"baseline":[107],"Unweighted":[108],"Average":[109],"Recall":[110],"(UAR)":[111],"score":[112],"achieve":[114],"comparable":[116],"result":[117],"state-of-the-art.":[120]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}