{"id":"https://openalex.org/W3024686730","doi":"https://doi.org/10.21437/interspeech.2020-1953","title":"Memory Controlled Sequential Self Attention for Sound Recognition","display_name":"Memory Controlled Sequential Self Attention for Sound Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3024686730","doi":"https://doi.org/10.21437/interspeech.2020-1953","mag":"3024686730"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1953","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.06650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091748859","display_name":"Arjun Pankajakshan","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Arjun Pankajakshan","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031962033","display_name":"Helen L. Bear","orcid":"https://orcid.org/0000-0002-6051-536X"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Helen L. Bear","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070172156","display_name":"Vinod Subramanian","orcid":"https://orcid.org/0000-0001-9818-7982"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vinod Subramanian","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, United Kingdom","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091748859"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04536528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"831","last_page":"835"},"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":0.9988999962806702,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282747030258179},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5826278924942017},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5421165227890015},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5103561282157898},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4429951012134552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35658013820648193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33077025413513184},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3273167014122009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282747030258179},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5826278924942017},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5421165227890015},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5103561282157898},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4429951012134552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35658013820648193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33077025413513184},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3273167014122009},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-1953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1953","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"},{"id":"pmh:oai:arXiv.org:2005.06650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06650","pdf_url":"https://arxiv.org/pdf/2005.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3024686730","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2005.06650.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/67665","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/67665","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"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 Proceeding"},{"id":"doi:10.48550/arxiv.2005.06650","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.06650","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.06650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.06650","pdf_url":"https://arxiv.org/pdf/2005.06650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3024686730.pdf","grobid_xml":"https://content.openalex.org/works/W3024686730.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1902237438","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2593116425","https://openalex.org/W2604490051","https://openalex.org/W2759976799","https://openalex.org/W2771361008","https://openalex.org/W2791956393","https://openalex.org/W2889769646","https://openalex.org/W2912056372","https://openalex.org/W2950178297","https://openalex.org/W2962826786","https://openalex.org/W2963022469","https://openalex.org/W2963403868","https://openalex.org/W2964308564","https://openalex.org/W2964891022"],"related_works":["https://openalex.org/W3097059024","https://openalex.org/W3015492205","https://openalex.org/W2765245454","https://openalex.org/W3109885824","https://openalex.org/W3198922001","https://openalex.org/W2952028139","https://openalex.org/W2558263348","https://openalex.org/W2545625743","https://openalex.org/W2795429538","https://openalex.org/W3004860304","https://openalex.org/W2952191002","https://openalex.org/W2989713682","https://openalex.org/W2961714142","https://openalex.org/W3036615999","https://openalex.org/W2105653685","https://openalex.org/W3132023005","https://openalex.org/W2979334631","https://openalex.org/W2952136670","https://openalex.org/W2910828319","https://openalex.org/W2210521895"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"investigate":[4],"the":[5,8,48,52,55,64,72,86,133,137,144],"importance":[6],"of":[7,10,32,54,57,97,111,130,140],"extent":[9,56],"memory":[11,24,58,98,119],"in":[12],"sequential":[13,26,100],"self":[14,27,65,78,101,121,147],"attention":[15,28,66,79,83,91,102,122],"for":[16,40],"sound":[17,42,60,112],"recognition.":[18],"We":[19,70,115],"propose":[20],"to":[21,106],"use":[22,96],"a":[23,33,76,104],"controlled":[25,99,120],"mechanism":[29,80],"on":[30,47,59,132],"top":[31],"convolutional":[34],"recurrent":[35],"neural":[36],"network":[37],"(CRNN)":[38],"model":[39,123,145],"polyphonic":[41],"event":[43,113,126],"detection":[44],"(SED).":[45],"Experiments":[46],"URBAN-SED":[49,134],"dataset":[50],"demonstrate":[51],"impact":[53],"recognition":[61],"performance":[62],"with":[63,75,89],"induced":[67],"SED":[68],"model.":[69],"extend":[71],"proposed":[73,95],"idea":[74],"multi-head":[77],"where":[81],"each":[82],"head":[84],"processes":[85],"audio":[87],"embedding":[88],"explicit":[90],"width":[92],"values.":[93],"The":[94],"offers":[103],"way":[105],"induce":[107],"relations":[108],"among":[109],"frames":[110],"tokens.":[114],"show":[116],"that":[117],"our":[118],"achieves":[124],"an":[125],"based":[127],"F":[128,138],"-score":[129,139],"33.92%":[131],"dataset,":[135],"outperforming":[136],"20.10%":[141],"reported":[142],"by":[143],"without":[146],"attention.":[148]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}