{"id":"https://openalex.org/W2081433959","doi":"https://doi.org/10.1109/hscma.2014.6843263","title":"Spectrogram patch based acoustic event detection and classification in speech overlapping conditions","display_name":"Spectrogram patch based acoustic event detection and classification in speech overlapping conditions","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2081433959","doi":"https://doi.org/10.1109/hscma.2014.6843263","mag":"2081433959"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2014.6843263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","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/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, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","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, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102252420","display_name":"Yotaro Kubo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]},{"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":["DE","JP"],"is_corresponding":false,"raw_author_name":"Yotaro Kubo","raw_affiliation_strings":["Amazon.com","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","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, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039277089"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.4557,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.82813495,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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":0.9991000294685364,"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/spectrogram","display_name":"Spectrogram","score":0.9304144382476807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7183434367179871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6915299296379089},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.537307620048523},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5286912322044373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3613627851009369},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.33531516790390015},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3216618299484253},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06588324904441833}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9304144382476807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7183434367179871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6915299296379089},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.537307620048523},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5286912322044373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3613627851009369},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.33531516790390015},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3216618299484253},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06588324904441833},{"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:10.1109/hscma.2014.6843263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"}],"best_oa_location":null,"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":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"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/W2086468861","https://openalex.org/W2089368853","https://openalex.org/W2114187103","https://openalex.org/W2115447976","https://openalex.org/W2126109423","https://openalex.org/W2128083002","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/W2398030828","https://openalex.org/W2400753342","https://openalex.org/W6601785968","https://openalex.org/W6683682394","https://openalex.org/W6684249834"],"related_works":["https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W4214896311","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Speech":[0],"does":[1],"not":[2],"always":[3],"contain":[4],"all":[5],"the":[6,20,41,48,118,144,160],"information":[7,39],"needed":[8],"to":[9,27,123],"understand":[10],"a":[11,57,104,132],"conversation":[12,58],"scene.":[13],"Non-speech":[14],"events":[15,55],"can":[16],"reveal":[17],"aspects":[18],"of":[19,50,97],"scene":[21,59],"that":[22,85,106,134,143,164],"speakers":[23],"miss":[24],"or":[25,75],"neglect":[26],"mention,":[28],"which":[29,78],"could":[30],"further":[31,169],"support":[32],"speech":[33,82],"enhancement":[34],"and":[35,52,89,114,125,138],"recognition":[36],"systems":[37],"with":[38,64,151],"about":[40],"surrounding":[42],"noise.":[43],"This":[44],"paper":[45],"focuses":[46],"on":[47,70,159],"task":[49],"detecting":[51],"classifying":[53],"acoustic":[54,127],"in":[56],"where":[60],"these":[61],"often":[62],"overlap":[63],"speech.":[65],"State-of-the-art":[66],"techniques":[67],"are":[68,93],"based":[69],"derived":[71,152],"features":[72,109,153],"(e.g.":[73],"MFCC,":[74],"Mel-filter":[76],"banks),":[77],"have":[79],"successfully":[80],"parameterized":[81],"spectrograms,":[83],"but":[84],"reduce":[86],"both":[87],"resolution":[88],"detail":[90],"when":[91],"we":[92,102],"targeting":[94],"other":[95],"kinds":[96],"events.":[98,128],"In":[99],"this":[100],"paper,":[101],"propose":[103],"method":[105,146],"learns":[107],"hidden":[108],"directly":[110],"from":[111],"spectrogram":[112],"patches,":[113],"integrates":[115],"them":[116],"within":[117],"deep":[119,148],"neural":[120,149],"network":[121],"framework":[122],"detect":[124],"classify":[126],"The":[129],"result":[130],"is":[131,166],"model":[133],"performs":[135],"feature":[136],"extraction":[137],"classification":[139],"simultaneously.":[140],"Experiments":[141],"confirm":[142],"proposed":[145],"outperforms":[147],"networks":[150],"as":[154,156],"well":[155],"related":[157],"work":[158],"CHIL2007-AED":[161],"task,":[162],"showing":[163],"there":[165],"room":[167],"for":[168],"improvement.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
