{"id":"https://openalex.org/W4387351339","doi":"https://doi.org/10.1587/transfun.2023ssl0001","title":"Noise-Robust Scream Detection Using Wave-U-Net","display_name":"Noise-Robust Scream Detection Using Wave-U-Net","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387351339","doi":"https://doi.org/10.1587/transfun.2023ssl0001"},"language":"en","primary_location":{"id":"doi:10.1587/transfun.2023ssl0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023ssl0001","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023SSL0001/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023SSL0001/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107899791","display_name":"Noboru Hayasaka","orcid":null},"institutions":[{"id":"https://openalex.org/I189513530","display_name":"Osaka Electro-Communication University","ror":"https://ror.org/056bksm23","country_code":"JP","type":"education","lineage":["https://openalex.org/I189513530"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Noboru HAYASAKA","raw_affiliation_strings":["Department of Engineering Informatics, Osaka Electro-Communication University"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Informatics, Osaka Electro-Communication University","institution_ids":["https://openalex.org/I189513530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026616194","display_name":"Riku Kasai","orcid":null},"institutions":[{"id":"https://openalex.org/I189513530","display_name":"Osaka Electro-Communication University","ror":"https://ror.org/056bksm23","country_code":"JP","type":"education","lineage":["https://openalex.org/I189513530"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Riku KASAI","raw_affiliation_strings":["OPTAGE Inc","Department of Engineering Informatics, Osaka Electro-Communication University"],"affiliations":[{"raw_affiliation_string":"OPTAGE Inc","institution_ids":[]},{"raw_affiliation_string":"Department of Engineering Informatics, Osaka Electro-Communication University","institution_ids":["https://openalex.org/I189513530"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039448889","display_name":"Takuya Futagami","orcid":"https://orcid.org/0000-0003-2981-1782"},"institutions":[{"id":"https://openalex.org/I189513530","display_name":"Osaka Electro-Communication University","ror":"https://ror.org/056bksm23","country_code":"JP","type":"education","lineage":["https://openalex.org/I189513530"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya FUTAGAMI","raw_affiliation_strings":["Department of Engineering Informatics, Osaka Electro-Communication University"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Informatics, Osaka Electro-Communication University","institution_ids":["https://openalex.org/I189513530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5107899791"],"corresponding_institution_ids":["https://openalex.org/I189513530"],"apc_list":null,"apc_paid":null,"fwci":0.2031,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45583586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"E107.A","issue":"4","first_page":"634","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.968999981880188,"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":0.968999981880188,"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":0.9376000165939331,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9146000146865845,"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/noise","display_name":"Noise (video)","score":0.648705244064331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5336974859237671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5198531746864319},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4940040707588196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4785912036895752},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.45559006929397583},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.45372581481933594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4366089105606079},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3913787007331848},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2716106176376343},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13961490988731384},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.055089354515075684}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.648705244064331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5336974859237671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5198531746864319},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4940040707588196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4785912036895752},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.45559006929397583},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.45372581481933594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4366089105606079},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3913787007331848},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2716106176376343},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13961490988731384},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.055089354515075684},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transfun.2023ssl0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023ssl0001","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023SSL0001/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transfun.2023ssl0001","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transfun.2023ssl0001","pdf_url":"https://www.jstage.jst.go.jp/article/transfun/advpub/0/advpub_2023SSL0001/_pdf","source":{"id":"https://openalex.org/S166990724","display_name":"IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences","issn_l":"0916-8508","issn":["0916-8508","1745-1337"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4444907211","display_name":"Development of a noise-robust scream detection system using deep learning","funder_award_id":"19K04935","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8430481527","display_name":null,"funder_award_id":"Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387351339.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1538203218","https://openalex.org/W2211849486","https://openalex.org/W2242832615","https://openalex.org/W2398932003","https://openalex.org/W2607414316","https://openalex.org/W2805288670","https://openalex.org/W2963341071","https://openalex.org/W3197276571"],"related_works":["https://openalex.org/W2033914206","https://openalex.org/W2146076056","https://openalex.org/W2163831990","https://openalex.org/W2368779261","https://openalex.org/W3003836766","https://openalex.org/W2553247019","https://openalex.org/W2073379399","https://openalex.org/W2971695076","https://openalex.org/W4378230932","https://openalex.org/W2952454517"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,19,35],"noise-robust":[6],"scream":[7,16,60],"detection":[8,17,81],"method":[9,25,38,86],"with":[10,108],"the":[11,15,43,69,84,94,109],"aim":[12],"of":[13,71,103],"expanding":[14],"system,":[18],"sound-based":[20],"security":[21],"system.":[22],"The":[23],"proposed":[24,85],"uses":[26],"enhanced":[27,44],"screams":[28,45,52],"using":[29,83],"Wave-U-Net,":[30],"which":[31,76],"was":[32,65,98],"effective":[33],"as":[34],"noise":[36,89],"reduction":[37],"for":[39],"noisy":[40],"screams.":[41],"However,":[42],"showed":[46],"different":[47],"frequency":[48,56],"components":[49,57],"from":[50],"clean":[51],"and":[53,91],"erroneously":[54],"emphasized":[55],"similar":[58],"to":[59],"in":[61,68,87],"noise.":[62],"Therefore,":[63],"Wave-U-Net":[64],"applied":[66],"even":[67],"process":[70],"training":[72],"Gaussian":[73],"mixture":[74],"models,":[75],"are":[77],"discriminators.":[78],"We":[79],"conducted":[80],"experiments":[82],"various":[88],"environments":[90],"determined":[92],"that":[93],"false":[95],"acceptance":[96],"rate":[97],"reduced":[99],"by":[100],"an":[101],"average":[102],"2.1%":[104],"or":[105],"more":[106],"compared":[107],"conventional":[110],"method.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}