{"id":"https://openalex.org/W2120085319","doi":"https://doi.org/10.1587/transinf.2014edp7430","title":"Acoustic Event Detection in Speech Overlapping Scenarios Based on High-Resolution Spectral Input and Deep Learning","display_name":"Acoustic Event Detection in Speech Overlapping Scenarios Based on High-Resolution Spectral Input and Deep Learning","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2120085319","doi":"https://doi.org/10.1587/transinf.2014edp7430","mag":"2120085319"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2014edp7430","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7430","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/10/E98.D_2014EDP7430/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/10/E98.D_2014EDP7430/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039277089","display_name":"Miquel Espi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miquel ESPI","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Laboratories, NTT Corporation,"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation,","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo FUJIMOTO","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Laboratories, NTT Corporation,"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation,","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro NAKATANI","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation","NTT Communication Science Laboratories, NTT Corporation,"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation,","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5039277089"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.8616,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7423041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"E98.D","issue":"10","first_page":"1799","last_page":"1807"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.872945249080658},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8576319217681885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7166838049888611},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5981285572052002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49095800518989563},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.48022136092185974},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45722901821136475},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4392293393611908},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35916921496391296},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.29360222816467285},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16202053427696228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.872945249080658},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8576319217681885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7166838049888611},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5981285572052002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49095800518989563},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.48022136092185974},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45722901821136475},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4392293393611908},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35916921496391296},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.29360222816467285},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16202053427696228},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2014edp7430","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7430","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/10/E98.D_2014EDP7430/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2014edp7430","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7430","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E98.D/10/E98.D_2014EDP7430/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"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 Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5699999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2120085319.pdf","grobid_xml":"https://content.openalex.org/works/W2120085319.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1822987211","https://openalex.org/W1976363263","https://openalex.org/W1977834503","https://openalex.org/W1988876483","https://openalex.org/W1993882792","https://openalex.org/W2000221426","https://openalex.org/W2005733316","https://openalex.org/W2008415856","https://openalex.org/W2059203007","https://openalex.org/W2081433959","https://openalex.org/W2086384421","https://openalex.org/W2086468861","https://openalex.org/W2089368853","https://openalex.org/W2114187103","https://openalex.org/W2115447976","https://openalex.org/W2123843894","https://openalex.org/W2126109423","https://openalex.org/W2128083002","https://openalex.org/W2128437937","https://openalex.org/W2134925458","https://openalex.org/W2141739745","https://openalex.org/W2146792684","https://openalex.org/W2160860215","https://openalex.org/W2165712214","https://openalex.org/W2168013545","https://openalex.org/W2359377300","https://openalex.org/W2398030828","https://openalex.org/W2400753342","https://openalex.org/W4247053610"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,31,46,51,136,150,153],"method":[3,137],"for":[4],"recognition":[5,81],"of":[6,57,116,129,156,205],"acoustic":[7,18,28,95,174],"events":[8,74],"in":[9,30,141,181],"conversation":[10,32],"scenarios":[11,91],"where":[12],"speech":[13,21,78,117],"usually":[14,23],"overlaps":[15],"with":[16,199],"other":[17,127],"events.":[19,130,175],"While":[20],"is":[22],"considered":[24],"the":[25,40,58,89,114,165,182],"most":[26],"informative":[27],"event":[29,96],"scene,":[33],"it":[34],"does":[35],"not":[36],"always":[37],"contain":[38],"all":[39],"information.":[41],"Non-speech":[42],"events,":[43],"such":[44],"as":[45,152],"door":[47],"knock,":[48],"steps,":[49],"or":[50,63,108],"keyboard":[52],"typing":[53],"can":[54],"reveal":[55],"aspects":[56],"scene":[59],"that":[60,138],"speakers":[61],"miss":[62],"avoid":[64],"to":[65,70,170],"mention.":[66],"Moreover,":[67],"being":[68],"able":[69],"robustly":[71],"detect":[72,171],"these":[73],"could":[75],"further":[76],"support":[77],"enhancement":[79],"and":[80,92,121,162,172,184,197],"systems":[82],"by":[83,194],"providing":[84],"useful":[85],"information":[86],"cues":[87],"about":[88],"surrounding":[90],"noise.":[93],"In":[94,131],"detection,":[97],"state-of-the-art":[98],"techniques":[99],"are":[100,125],"typically":[101],"based":[102,187],"on":[103,188],"derived":[104,189],"features":[105,140,159],"(e.g.":[106],"MFCC,":[107],"Mel-filter-banks)":[109],"which":[110],"have":[111],"successfully":[112],"parameterized":[113],"spectrogram":[115,147],"but":[118],"reduce":[119],"resolution":[120],"detail":[122],"when":[123],"we":[124,134],"targeting":[126],"kinds":[128],"this":[132],"paper,":[133],"propose":[135],"learns":[139],"an":[142,202],"unsupervised":[143],"manner":[144],"from":[145],"high-resolution":[146],"patches":[148],"(considering":[149],"patch":[151],"certain":[154],"number":[155],"consecutive":[157],"frame":[158],"stacked":[160],"together),":[161],"integrates":[163],"within":[164],"deep":[166],"neural":[167],"network":[168],"framework":[169],"classify":[173],"Superiority":[176],"over":[177],"both":[178],"previous":[179],"works":[180],"field,":[183],"similar":[185],"approaches":[186],"features,":[190],"has":[191],"been":[192],"assessed":[193],"statical":[195],"measures":[196],"evaluation":[198],"CHIL2007":[200],"corpus,":[201],"annotated":[203],"database":[204],"seminar":[206],"recordings.":[207]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}