{"id":"https://openalex.org/W2604490051","doi":"https://doi.org/10.21437/interspeech.2017-486","title":"Attention and Localization Based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging","display_name":"Attention and Localization Based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2604490051","doi":"https://doi.org/10.21437/interspeech.2017-486","mag":"2604490051"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-486","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5102746357","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0001-9934-3369"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013817745","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-1120-4685"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Center for Vision, Speech and Signal Processing, University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision, Speech and Signal Processing, University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102746357"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":8.3947,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.98256487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3083","last_page":"3087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9959999918937683,"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":0.9952999949455261,"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":0.8213738799095154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6820904016494751},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6577879190444946},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5848429799079895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5805433988571167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.565812349319458},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5307331681251526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5138483643531799},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47623851895332336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.057033926248550415},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05536133050918579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8213738799095154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6820904016494751},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6577879190444946},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5848429799079895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5805433988571167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.565812349319458},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5307331681251526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138483643531799},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47623851895332336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.057033926248550415},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05536133050918579},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-486","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-486","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11138791980002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:841234","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/841234/1/IS2017_att_loc_at_final.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1503398984","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W2008415856","https://openalex.org/W2086384421","https://openalex.org/W2133564696","https://openalex.org/W2148577181","https://openalex.org/W2150355110","https://openalex.org/W2157331557","https://openalex.org/W2176625348","https://openalex.org/W2306289963","https://openalex.org/W2354870669","https://openalex.org/W2398826216","https://openalex.org/W2464737488","https://openalex.org/W2524365899","https://openalex.org/W2529483679","https://openalex.org/W2561826558","https://openalex.org/W2592944988","https://openalex.org/W2593116425","https://openalex.org/W2604293017","https://openalex.org/W2951527505","https://openalex.org/W2962826786","https://openalex.org/W3103455452"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"Audio":[0],"tagging":[1,52],"aims":[2],"to":[3,33,70,90,145],"perform":[4],"multi-label":[5],"classification":[6],"on":[7,45,134],"audio
\\nchunks":[8],"and":[9,23,35],"it":[10],"is":[11,53,88,104],"a":[12,57,61,66,105,116],"newly":[13],"proposed":[14,102,120],"task":[15,29],"in":[16,50],"the":[17,37,40,46,78,82,94,99,124,135],"Detection":[18],"and
\\nClassification":[19],"of":[20,39,81,127],"Acoustic":[21],"Scenes":[22],"Events":[24],"2016":[25,129],"(DCASE
\\n2016)":[26],"challenge.":[27,130],"This":[28],"encourages":[30],"research":[31],"efforts":[32],"better
\\nanalyze":[34],"understand":[36],"content":[38],"huge":[41],"amounts":[42],"of
\\naudio":[43],"data":[44],"web.":[47],"The":[48,85,101,119],"difficulty":[49],"audio":[51],"that
\\nit":[54],"only":[55,72],"has":[56],"chunk-level":[58],"label":[59],"without":[60],"frame-level":[62],"label.":[63],"This
\\npaper":[64],"presents":[65],"weakly":[67],"supervised":[68],"method":[69],"not":[71],"predict
\\nthe":[73],"tags":[74],"but":[75],"also":[76],"indicate":[77],"temporal":[79],"locations":[80],"occurred
\\nacoustic":[83],"events.":[84],"attention":[86,114],"scheme":[87],"found":[89],"be":[91],"effective
\\nin":[92],"identifying":[93],"important":[95],"frames":[96],"while":[97],"ignoring":[98],"unrelated
\\nframes.":[100],"framework":[103],"deep":[106],"convolutional":[107],"recurrent
\\nmodel":[108],"with":[109,138,148],"two":[110],"auxiliary":[111],"modules:":[112],"an":[113],"module
\\nand":[115],"localization":[117],"module.":[118],"algorithm":[121],"was":[122,132],"evaluated
\\non":[123],"Task":[125],"4":[126],"DCASE":[128],"State-of-the-art
\\nperformance":[131],"achieved":[133],"evaluation":[136],"set":[137],"equal":[139],"error
\\nrate":[140],"(EER)":[141],"reduced":[142],"from":[143],"0.13":[144],"0.11,":[146],"compared":[147],"the
\\nconvolutional":[149],"recurrent":[150],"baseline":[151],"system.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}