{"id":"https://openalex.org/W4225299287","doi":"https://doi.org/10.1109/icassp43922.2022.9746828","title":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","display_name":"Vocalsound: A Dataset for Improving Human Vocal Sounds Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225299287","doi":"https://doi.org/10.1109/icassp43922.2022.9746828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746828","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2205.03433","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067285379","display_name":"Yuan Gong","orcid":"https://orcid.org/0000-0002-4537-0078"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Gong","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA,02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4405258931"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100417330","display_name":"Yu Jin","orcid":"https://orcid.org/0000-0003-2179-5634"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Yu","raw_affiliation_strings":["Signify Research,Cambridge,MA,USA,02142"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signify Research,Cambridge,MA,USA,02142","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL,Cambridge,MA,USA,02139"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT CSAIL,Cambridge,MA,USA,02139","institution_ids":["https://openalex.org/I4405258931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7224,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97277228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9980999827384949,"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/speech-recognition","display_name":"Speech recognition","score":0.7516947984695435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259344458580017},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5598618984222412},{"id":"https://openalex.org/keywords/laughter","display_name":"Laughter","score":0.4768696427345276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39012590050697327},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08101797103881836},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07045340538024902}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7516947984695435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259344458580017},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5598618984222412},{"id":"https://openalex.org/C2780775679","wikidata":"https://www.wikidata.org/wiki/Q170579","display_name":"Laughter","level":2,"score":0.4768696427345276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39012590050697327},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08101797103881836},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07045340538024902},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746828","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746828","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2205.03433","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03433","pdf_url":"https://arxiv.org/pdf/2205.03433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2205.03433","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2205.03433","pdf_url":"https://arxiv.org/pdf/2205.03433","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2026150550","https://openalex.org/W2052666245","https://openalex.org/W2167700723","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2798579254","https://openalex.org/W2936774411","https://openalex.org/W2955425717","https://openalex.org/W2995161242","https://openalex.org/W3015034944","https://openalex.org/W3021910945","https://openalex.org/W3035378948","https://openalex.org/W3068613985","https://openalex.org/W3081012644","https://openalex.org/W3087180772","https://openalex.org/W3088067841","https://openalex.org/W3091468319","https://openalex.org/W3094550259","https://openalex.org/W3104211335","https://openalex.org/W3105837102","https://openalex.org/W3117598648","https://openalex.org/W3134945014","https://openalex.org/W3196831814","https://openalex.org/W3205743929","https://openalex.org/W4205689591","https://openalex.org/W4206458399","https://openalex.org/W4398958419","https://openalex.org/W6631190155","https://openalex.org/W6747331233","https://openalex.org/W6750883802","https://openalex.org/W6762718338","https://openalex.org/W6783462664","https://openalex.org/W6783737571","https://openalex.org/W6783903196"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2760111529","https://openalex.org/W4304693785","https://openalex.org/W3081604601","https://openalex.org/W2391280397","https://openalex.org/W4238600753","https://openalex.org/W2103493245","https://openalex.org/W4298012685","https://openalex.org/W2063843262"],"abstract_inverted_index":{"Recognizing":[0],"human":[1,50],"non-speech":[2],"vocalizations":[3],"is":[4],"an":[5,111],"important":[6],"task":[7],"and":[8,17,59,83,137],"has":[9],"broad":[10],"applications":[11],"such":[12,129],"as":[13,114,130],"automatic":[14],"sound":[15,31,62,94],"transcription":[16],"health":[18,138],"condition":[19],"monitoring.":[20],"However,":[21],"existing":[22,112],"datasets":[23],"have":[24,65],"a":[25,37,67,98],"relatively":[26],"small":[27],"number":[28],"of":[29,71,76,97],"vocal":[30,51,61,93],"samples":[32],"or":[33],"noisy":[34],"labels.":[35],"As":[36],"consequence,":[38],"state-of-the-art":[39],"audio":[40],"event":[41],"classification":[42],"models":[43],"may":[44],"not":[45],"perform":[46],"well":[47],"in":[48],"detecting":[49],"sounds.":[52],"To":[53],"support":[54],"research":[55],"on":[56],"building":[57],"robust":[58],"accurate":[60],"recognition,":[63],"we":[64],"created":[66],"VocalSound":[68,108,124],"dataset":[69,109,113,125],"consisting":[70],"over":[72],"21,000":[73],"crowdsourced":[74],"recordings":[75],"laughter,":[77],"sighs,":[78],"coughs,":[79],"throat":[80],"clearing,":[81],"sneezes,":[82],"sniffs":[84],"from":[85,120],"3,365":[86],"unique":[87],"subjects.":[88],"Experiments":[89],"show":[90],"that":[91],"the":[92,123],"recognition":[95],"performance":[96],"model":[99],"can":[100],"be":[101],"significantly":[102],"improved":[103],"by":[104,106],"41.9%":[105],"adding":[107],"to":[110],"training":[115],"material.":[116],"In":[117],"addition,":[118],"different":[119],"previous":[121],"datasets,":[122],"contains":[126],"meta":[127],"information":[128],"speaker":[131],"age,":[132],"gender,":[133],"native":[134],"language,":[135],"country,":[136],"condition.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}