{"id":"https://openalex.org/W4401328965","doi":"https://doi.org/10.1109/chase60773.2024.00023","title":"Sound Tagging in Infant-centric Home Soundscapes","display_name":"Sound Tagging in Infant-centric Home Soundscapes","publication_year":2024,"publication_date":"2024-06-19","ids":{"openalex":"https://openalex.org/W4401328965","doi":"https://doi.org/10.1109/chase60773.2024.00023"},"language":"en","primary_location":{"id":"doi:10.1109/chase60773.2024.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chase60773.2024.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)","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/A5101384237","display_name":"Mohammad Nur Hossain Khan","orcid":"https://orcid.org/0000-0002-8312-7001"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Nur Hossain Khan","raw_affiliation_strings":["Worcester Polytechnic Institute,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I107077323"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456945","display_name":"Jialu Li","orcid":"https://orcid.org/0000-0003-0092-8071"},"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":"Jialu Li","raw_affiliation_strings":["University of Illinois,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040993718","display_name":"Nancy L. McElwain","orcid":"https://orcid.org/0000-0001-9586-5020"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nancy L. McElwain","raw_affiliation_strings":["University of Illinois,Department of Human Development and Family Studies"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Department of Human Development and Family Studies","institution_ids":[]}]},{"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\u2013Johnson","raw_affiliation_strings":["University of Illinois,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035909313","display_name":"Bashima Islam","orcid":"https://orcid.org/0000-0002-1917-054X"},"institutions":[{"id":"https://openalex.org/I107077323","display_name":"Worcester Polytechnic Institute","ror":"https://ror.org/05ejpqr48","country_code":"US","type":"education","lineage":["https://openalex.org/I107077323"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bashima Islam","raw_affiliation_strings":["Worcester Polytechnic Institute,Department of Electrical and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Worcester Polytechnic Institute,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I107077323"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9172,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7298214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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/T13289","display_name":"Infant Health and Development","score":0.9962000250816345,"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":0.9891999959945679,"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/soundscape","display_name":"Soundscape","score":0.7887967824935913},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.6740561127662659},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5849675536155701},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3815120756626129},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08487969636917114}],"concepts":[{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.7887967824935913},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.6740561127662659},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5849675536155701},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3815120756626129},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08487969636917114}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/chase60773.2024.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chase60773.2024.00023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2010676081","https://openalex.org/W2033875152","https://openalex.org/W2052666245","https://openalex.org/W2053154970","https://openalex.org/W2108598243","https://openalex.org/W2129120544","https://openalex.org/W2133824856","https://openalex.org/W2176625348","https://openalex.org/W2191779130","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2762841950","https://openalex.org/W2955876131","https://openalex.org/W2962785008","https://openalex.org/W2964244604","https://openalex.org/W2972359262","https://openalex.org/W3010360545","https://openalex.org/W3158553615","https://openalex.org/W3196974791","https://openalex.org/W3216401400","https://openalex.org/W4224216166","https://openalex.org/W4296737674","https://openalex.org/W4385245566","https://openalex.org/W4385807453","https://openalex.org/W4385822277","https://openalex.org/W4387183160","https://openalex.org/W4390056036","https://openalex.org/W6788135285","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2365709658","https://openalex.org/W1562588264","https://openalex.org/W1593731728"],"abstract_inverted_index":{"Certain":[0],"environmental":[1,169,177],"noises":[2,128],"have":[3,64,124],"been":[4],"associated":[5],"with":[6,231,268],"negative":[7],"developmental":[8],"outcomes":[9],"for":[10,98],"infants":[11,56],"and":[12,126,191,195,200,213,241,249,256],"young":[13,58],"children.":[14],"Though":[15],"classifying":[16],"or":[17,44,57,63,86,270],"tagging":[18],"sound":[19,77],"events":[20],"in":[21,41,60,111,129,135],"a":[22,37,69,157,207],"domestic":[23],"environment":[24,43,62],"is":[25,114],"an":[26,136,145],"active":[27],"research":[28],"area,":[29],"previous":[30],"studies":[31],"focused":[32],"on":[33,107,165,211],"data":[34,65,141,170,196],"collected":[35,66,125,143,229,271],"from":[36,45,67,74,132,237,252],"non-stationary":[38],"microphone":[39],"placed":[40],"the":[42,46,61,75,83,91,102,112,140,154,204,222,235],"perspective":[47],"of":[48,52,94,104,156,206],"adults.":[49],"Further,":[50],"many":[51],"these":[53,105],"works":[54],"ignore":[55],"children":[59],"only":[68,266],"single":[70],"family":[71],"where":[72,139],"noise":[73,99,109,199],"fixed":[76],"source":[78],"can":[79],"be":[80,117],"moderate":[81],"at":[82],"infant's":[84],"position":[85],"vice":[87],"versa.":[88],"Thus,":[89],"despite":[90],"recent":[92],"success":[93],"large":[95,158,208,223],"pre-trained":[96,159,209,224],"models":[97,106],"event":[100],"detection,":[101],"performance":[103,155,205],"infant-centric":[108,168,192,215],"soundscapes":[110,131],"home":[113,130,176],"yet":[115],"to":[116,245,260,265],"explored.":[118],"To":[119],"bridge":[120],"this":[121,150],"gap,":[122],"we":[123,152,202],"labeled":[127],"22":[133],"families":[134],"unobtrusive":[137],"manner,":[138],"are":[142],"through":[144],"infant-worn":[146],"recording":[147],"device.":[148],"In":[149],"paper,":[151],"explore":[153],"model":[160,210,225],"(Audio":[161],"Spectrogram":[162],"Transformer":[163],"[AST])":[164],"our":[166,228],"noise-conditioned":[167],"as":[171,173,184],"well":[172],"publicly":[174],"available":[175],"datasets.":[178],"Utilizing":[179],"different":[180],"training":[181,193,267],"strategies":[182],"such":[183],"resampling,":[185],"utilizing":[186],"public":[187,190,232,269],"datasets,":[188,272],"mixing":[189],"sets,":[194],"augmentation":[197],"using":[198],"masking,":[201],"evaluate":[203],"sparse":[212],"imbalanced":[214],"data.":[216],"Our":[217],"results":[218],"show":[219],"that":[220],"fine-tuning":[221],"by":[226],"combining":[227],"dataset":[230],"datasets":[233],"increases":[234],"F1-score":[236],"0.11":[238],"(public":[239,254],"datasets)":[240,244,248,255,259,263],"0.76":[242],"(collected":[243,258],"0.84":[246],"(combined":[247,262],"Cohen's":[250],"Kappa":[251],"0.013":[253],"0.77":[257],"0.83":[261],"compared":[264],"respectively.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}