{"id":"https://openalex.org/W3095513995","doi":"https://doi.org/10.21437/interspeech.2020-1552","title":"Learning Higher Representations from Pre-Trained Deep Models with Data Augmentation for the COMPARE 2020 Challenge Mask Task","display_name":"Learning Higher Representations from Pre-Trained Deep Models with Data Augmentation for the COMPARE 2020 Challenge Mask Task","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095513995","doi":"https://doi.org/10.21437/interspeech.2020-1552","mag":"3095513995"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1552","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1552","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":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/90750/koike20_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055581099","display_name":"Tomoya Koike","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoya Koike","raw_affiliation_strings":["Educational Physiology Laboratory, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Educational Physiology Laboratory, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032971738","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0002-1918-6453"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Educational Physiology Laboratory, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Educational Physiology Laboratory, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn W. Schuller","raw_affiliation_strings":["Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","GLAM -Group on Language, Audio, & Music, Imperial College London, UK"],"affiliations":[{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"GLAM -Group on Language, Audio, & Music, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087660235","display_name":"Yoshiharu Yamamoto","orcid":"https://orcid.org/0000-0002-1132-0355"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiharu Yamamoto","raw_affiliation_strings":["Educational Physiology Laboratory, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Educational Physiology Laboratory, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055581099"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.8261,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86170282,"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":"2047","last_page":"2051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9948999881744385,"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":0.9868999719619751,"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":0.7970917224884033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7092335224151611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6939865946769714},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5970988869667053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5877492427825928},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5485693216323853},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5459160208702087},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5341576337814331},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.494123250246048},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48213741183280945},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4619169235229492},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45169684290885925},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4440627694129944},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41969138383865356},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4131910800933838},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41301143169403076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06930553913116455}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7970917224884033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7092335224151611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6939865946769714},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5970988869667053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5877492427825928},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5485693216323853},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5459160208702087},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5341576337814331},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.494123250246048},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48213741183280945},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4619169235229492},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45169684290885925},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4440627694129944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41969138383865356},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4131910800933838},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41301143169403076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06930553913116455},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1552","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1552","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:uni-augsburg.opus-bayern.de:90750","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/90750","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/90750/koike20_interspeech.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:90750","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/90750","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/90750/koike20_interspeech.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1492856601","display_name":null,"funder_award_id":"Grants-in-Aid for Scientific Resear","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3481883747","display_name":null,"funder_award_id":"17H00878","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5024732792","display_name":null,"funder_award_id":"Postdoctoral Fellowship for Research in Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5256887504","display_name":null,"funder_award_id":"Japan Society for the Promotion of Science (JSPS)","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5612655108","display_name":null,"funder_award_id":"17H00878","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G576142307","display_name":null,"funder_award_id":"19F19081","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G6063292424","display_name":null,"funder_award_id":"19F19081","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6431078942","display_name":null,"funder_award_id":"Postdoctoral Fellowship for Researc","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7426172400","display_name":null,"funder_award_id":"P19081","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7482275571","display_name":null,"funder_award_id":"Ministry of Education, Culture, Sports, Science and Technology","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7693551792","display_name":null,"funder_award_id":"(MEXT)","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8538514152","display_name":null,"funder_award_id":"19081","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095513995.pdf"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W567437002","https://openalex.org/W1522301498","https://openalex.org/W1989674786","https://openalex.org/W2003304280","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2154579312","https://openalex.org/W2165698076","https://openalex.org/W2184343439","https://openalex.org/W2194775991","https://openalex.org/W2538918575","https://openalex.org/W2593116425","https://openalex.org/W2746419079","https://openalex.org/W2746502628","https://openalex.org/W2765407302","https://openalex.org/W2796101164","https://openalex.org/W2799149040","https://openalex.org/W2804935296","https://openalex.org/W2901215769","https://openalex.org/W2936774411","https://openalex.org/W2951696358","https://openalex.org/W2964121744","https://openalex.org/W2964182121","https://openalex.org/W2972850640","https://openalex.org/W2973025177","https://openalex.org/W3012958766","https://openalex.org/W3024152459","https://openalex.org/W3027265670","https://openalex.org/W3046779950","https://openalex.org/W3082319384","https://openalex.org/W3094550259","https://openalex.org/W3096215591","https://openalex.org/W4288091849","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2791025012","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W2021633306","https://openalex.org/W3171384686","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W3019226033"],"abstract_inverted_index":{"Human":[0],"hand-crafted":[1],"features":[2,20,37,60],"are":[3,119],"always":[4],"regarded":[5],"as":[6],"expensive,":[7],"time-consuming,":[8],"and":[9,116,185],"difficult":[10],"in":[11,39,190],"almost":[12],"all":[13],"of":[14,58,125,166,179],"the":[15,31,36,82,88,114,123,126,132,143,156,159,167,170,180,186,191],"machinelearning-related":[16],"tasks.First,":[17],"those":[18],"well-designed":[19],"extremely":[21],"rely":[22],"on":[23,71,93,105,155,169],"human":[24],"expert":[25],"domain":[26],"knowledge,":[27],"which":[28,54],"may":[29,44],"restrain":[30],"collaboration":[32],"work":[33],"across":[34],"fields.Second,":[35],"extracted":[38],"such":[40],"a":[41,56,68,72,101,176],"brute-force":[42],"scenario":[43],"not":[45],"be":[46,49,62],"easy":[47],"to":[48,51,121,152],"transferred":[50],"another":[52],"task,":[53],"means":[55],"series":[57],"new":[59],"should":[61],"designed.To":[63],"this":[64],"end,":[65],"we":[66,99],"introduce":[67],"method":[69],"based":[70,92,104],"transfer":[73],"learning":[74],"strategy":[75],"combined":[76],"with":[77],"data":[78],"augmentation":[79],"techniques":[80],"for":[81],"COMPARE":[83],"2020":[84],"Challenge":[85],"Mask":[86],"Sub-Challenge.Unlike":[87],"previous":[89],"studies":[90],"mainly":[91],"pre-trained":[94,102],"models":[95,184],"by":[96,175],"image":[97],"data,":[98,109],"use":[100],"model":[103,134,189],"large":[106],"scale":[107],"audio":[108],"i.":[110,162],"e.,":[111,163],"AudioSet.In":[112],"addition,":[113],"SpecAugment":[115],"mixup":[117],"methods":[118],"used":[120],"improve":[122,142],"generalisation":[124],"deep":[127],"models.Experimental":[128],"results":[129],"demonstrate":[130],"that":[131],"best-proposed":[133],"can":[135],"significantly":[136],"(p":[137],"<":[138],".001,by":[139],"one-tailed":[140],"z-test)":[141],"unweighted":[144],"average":[145],"recall":[146],"(UAR)":[147],"from":[148],"71.8":[149],"%":[150,154,165],"(baseline)":[151],"76.2":[153],"test":[157,171],"set.Finally,":[158],"best":[160,182,187],"result,":[161],"77.5":[164],"UAR":[168],"set,":[172],"is":[173],"achieved":[174],"late":[177],"fusion":[178],"two":[181],"proposed":[183],"single":[188],"baseline.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}