{"id":"https://openalex.org/W3095041945","doi":"https://doi.org/10.21437/interspeech.2020-1342","title":"Acoustic Scene Analysis with Multi-Head Attention Networks","display_name":"Acoustic Scene Analysis with Multi-Head Attention Networks","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095041945","doi":"https://doi.org/10.21437/interspeech.2020-1342","mag":"3095041945"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5042192401","display_name":"Weimin Wang","orcid":"https://orcid.org/0000-0001-6557-7175"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weimin Wang","raw_affiliation_strings":["Amazon Alexa 101 Main St, Cambridge, MA 02142, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa 101 Main St, Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101432591","display_name":"Weiran Wang","orcid":"https://orcid.org/0009-0000-0843-707X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiran Wang","raw_affiliation_strings":["Amazon Alexa 101 Main St, Cambridge, MA 02142, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa 101 Main St, Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100755311","display_name":"Ming Sun","orcid":"https://orcid.org/0000-0002-5948-2708"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Sun","raw_affiliation_strings":["Amazon Alexa 101 Main St, Cambridge, MA 02142, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa 101 Main St, Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406892","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0001-7578-1970"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Amazon Alexa 101 Main St, Cambridge, MA 02142, USA"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa 101 Main St, Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042192401"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54963792,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1191","last_page":"1195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.9980000257492065,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9750999808311462,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6918644905090332},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.6073771119117737},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40142107009887695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34777265787124634},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3206895887851715},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.10868126153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6918644905090332},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.6073771119117737},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40142107009887695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34777265787124634},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3206895887851715},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.10868126153945923},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1342","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2095705004","https://openalex.org/W2133564696","https://openalex.org/W2160335114","https://openalex.org/W2163605009","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2593116425","https://openalex.org/W2775505379","https://openalex.org/W2799258971","https://openalex.org/W2883618873","https://openalex.org/W2885392124","https://openalex.org/W2888283879","https://openalex.org/W2963438834","https://openalex.org/W2963610932","https://openalex.org/W3036237438","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2772917594","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Acoustic":[0],"Scene":[1],"Classification":[2],"(ASC)":[3],"is":[4,39,125],"a":[5,9,22,64],"challenging":[6],"task,":[7],"as":[8,84],"single":[10],"scene":[11,24,121],"may":[12,25],"involve":[13],"multiple":[14,102],"events":[15,111],"that":[16,40,135],"contain":[17,26],"complex":[18,71],"sound":[19,28,110,140],"patterns.For":[20],"example,":[21],"cooking":[23,52],"several":[27],"sources":[29],"including":[30],"silverware":[31,57],"clinking,":[32],"chopping,":[33],"frying,":[34],"etc.What":[35],"complicates":[36],"ASC":[37],"more":[38],"classes":[41],"of":[42,109,119],"different":[43],"activities":[44],"could":[45,55],"have":[46,56],"overlapping":[47],"sounds":[48],"patterns":[49,108,141],"(e.g.":[50],"both":[51],"and":[53,86,163],"dishwashing":[54],"clinking":[58],"sound).In":[59],"this":[60],"paper,":[61],"we":[62],"propose":[63],"multihead":[65],"attention":[66,103,144],"network":[67,78,124],"to":[68,94,105],"model":[69,137,156],"the":[70,80,117,143,151],"temporal":[72],"input":[73],"structures":[74],"for":[75,116],"ASC.The":[76],"proposed":[77,155],"takes":[79],"audio's":[81],"time-frequency":[82],"representation":[83],"input,":[85],"it":[87,100],"leverages":[88],"standard":[89],"VGG":[90],"plus":[91],"LSTM":[92],"layers":[93],"extract":[95],"high-level":[96],"feature":[97],"representation.Further":[98],"more,":[99],"applies":[101],"heads":[104],"summarize":[106],"various":[107],"into":[112],"fixed":[113],"dimensional":[114],"representation,":[115],"purpose":[118],"final":[120],"classification.The":[122],"whole":[123],"trained":[126],"in":[127,150],"an":[128],"end-to-end":[129],"fashion":[130],"with":[131,169],"backpropagation.Experimental":[132],"results":[133],"confirm":[134],"our":[136,154],"discovers":[138],"meaningful":[139],"through":[142],"mechanism,":[145],"without":[146],"using":[147,157],"explicit":[148],"supervision":[149],"alignment.We":[152],"evaluated":[153],"DCASE":[158],"2018":[159],"Task":[160],"5":[161],"dataset,":[162],"achieved":[164],"competitive":[165],"performance":[166],"on":[167],"par":[168],"previous":[170],"winner's":[171],"results.":[172]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
