{"id":"https://openalex.org/W4283311932","doi":"https://doi.org/10.21437/interspeech.2022-767","title":"A Multi-grained based Attention Network for Semi-supervised Sound Event Detection","display_name":"A Multi-grained based Attention Network for Semi-supervised Sound Event Detection","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283311932","doi":"https://doi.org/10.21437/interspeech.2022-767"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-767","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.10175","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","Key Laboratory of signal detection and processing in Xinjiang, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Key Laboratory of signal detection and processing in Xinjiang, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089534179","display_name":"Xiujuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiujuan Zhu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Key Laboratory of signal detection and processing in Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of signal detection and processing in Xinjiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402198","display_name":"Yunlong Li","orcid":"https://orcid.org/0000-0002-7193-7322"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlong Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China","Key Laboratory of signal detection and processing in Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of signal detection and processing in Xinjiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757355","display_name":"Hao Huang","orcid":"https://orcid.org/0009-0005-7353-3072"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["School of Information Science and Engineering, Xinjiang University, Urumqi, China","Key Laboratory of signal detection and processing in Xinjiang, China","Department of Electronic Engineering, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Key Laboratory of signal detection and processing in Xinjiang, China","institution_ids":[]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010540039","display_name":"Liang He","orcid":"https://orcid.org/0000-0002-4723-5486"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang He","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China","Key Laboratory of signal detection and processing in Xinjiang, China","School of Information Science and Engineering, Xinjiang University, Urumqi, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Key Laboratory of signal detection and processing in Xinjiang, China","institution_ids":[]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, Urumqi, China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":["https://openalex.org/I96908189","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2212,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.81391688,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1531","last_page":"1535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9772999882698059,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9757999777793884,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7209887504577637},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.47402527928352356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43686652183532715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4330427944660187},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.42977991700172424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3870193362236023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21144402027130127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209887504577637},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47402527928352356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43686652183532715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4330427944660187},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.42977991700172424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3870193362236023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21144402027130127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-767","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-767","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2206.10175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10175","pdf_url":"https://arxiv.org/pdf/2206.10175","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.10175","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.10175","pdf_url":"https://arxiv.org/pdf/2206.10175","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2135131618","https://openalex.org/W2296193698","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2890685186","https://openalex.org/W2899663614","https://openalex.org/W2951970475","https://openalex.org/W2953070460","https://openalex.org/W2963558289","https://openalex.org/W2964110616","https://openalex.org/W2964159205","https://openalex.org/W2981609437","https://openalex.org/W2995135322","https://openalex.org/W3015190346","https://openalex.org/W3015387077","https://openalex.org/W3015792128","https://openalex.org/W3016195076","https://openalex.org/W3017521796","https://openalex.org/W3093712593","https://openalex.org/W3095994161","https://openalex.org/W3109837239","https://openalex.org/W3124216180","https://openalex.org/W3182910640","https://openalex.org/W3189759539","https://openalex.org/W3209458476","https://openalex.org/W4288099153","https://openalex.org/W4288265053","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2017572878","https://openalex.org/W3022853057","https://openalex.org/W2377728464","https://openalex.org/W4388308858","https://openalex.org/W2046645015","https://openalex.org/W2747473526","https://openalex.org/W615465616","https://openalex.org/W2745139775","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Sound":[0],"event":[1,35],"detection":[2,165],"(SED)":[3],"is":[4,52,71,132],"an":[5],"interesting":[6],"but":[7],"challenging":[8],"task":[9],"due":[10],"to":[11,43,54,60,73,80,111,134],"the":[12,39,56,62,83,89,103,114,117,136,144,147,169],"scarcity":[13],"of":[14,91,107,116,138],"data":[15,129],"and":[16,105,153,161,171],"diverse":[17],"sound":[18,34,44,108,164],"events":[19,93],"in":[20,99],"real":[21],"life.":[22],"This":[23],"paper":[24],"presents":[25],"a":[26,46,66,122,128],"multi-grained":[27,67],"based":[28],"attention":[29,68],"network":[30,86],"(MGA-Net)":[31],"for":[32],"semi-supervised":[33],"detection.":[36],"To":[37],"obtain":[38],"feature":[40],"representations":[41],"related":[42],"events,":[45],"residual":[47],"hybrid":[48],"convolution":[49],"(RH-Conv)":[50],"block":[51],"designed":[53,72],"boost":[55,113],"vanilla":[57],"convolution's":[58],"ability":[59],"extract":[61],"time-frequency":[63],"features.":[64],"Moreover,":[65],"(MGA)":[69],"module":[70,126],"learn":[74],"temporal":[75],"resolution":[76],"features":[77],"from":[78],"coarse-level":[79],"fine-level.":[81],"With":[82],"MGA":[84],"module,the":[85],"could":[87],"capture":[88],"characteristics":[90],"target":[92],"with":[94],"short-":[95],"or":[96],"long-duration,":[97],"resulting":[98],"more":[100],"accurately":[101],"determining":[102],"onset":[104],"offset":[106],"events.":[109],"Furthermore,":[110],"effectively":[112],"performance":[115],"Mean":[118],"Teacher":[119],"(MT)":[120],"method,":[121],"spatial":[123],"shift":[124],"(SS)":[125],"as":[127],"perturbation":[130],"mechanism":[131],"introduced":[133],"increase":[135],"diversity":[137],"data.":[139],"Experimental":[140],"results":[141],"show":[142],"that":[143],"MGA-Net":[145],"outperforms":[146],"published":[148],"state-of-the-art":[149],"competitors,":[150],"achieving":[151],"53.27%":[152],"56.96%":[154],"event-based":[155],"macro":[156],"F1":[157],"(EB-F1)":[158],"score,":[159],"0.709":[160],"0.739":[162],"polyphonic":[163],"score":[166],"(PSDS)":[167],"on":[168],"validation":[170],"public":[172],"set":[173],"respectively.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2022-06-24T00:00:00"}