{"id":"https://openalex.org/W3095398221","doi":"https://doi.org/10.21437/interspeech.2020-2666","title":"Ensembling End-to-End Deep Models for Computational Paralinguistics Tasks: ComParE 2020 Mask and Breathing Sub-Challenges","display_name":"Ensembling End-to-End Deep Models for Computational Paralinguistics Tasks: ComParE 2020 Mask and Breathing Sub-Challenges","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095398221","doi":"https://doi.org/10.21437/interspeech.2020-2666","mag":"3095398221"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2666","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2666","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/A5050029665","display_name":"Maxim Markitantov","orcid":"https://orcid.org/0000-0001-7987-1025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maxim Markitantov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031192722","display_name":"Denis Dresvyanskiy","orcid":"https://orcid.org/0000-0002-5141-2561"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Denis Dresvyanskiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060877179","display_name":"Danila Mamontov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danila Mamontov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050585145","display_name":"Heysem Kaya","orcid":"https://orcid.org/0000-0001-7947-5508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heysem Kaya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110317553","display_name":"Wolfgang Minker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolfgang Minker","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032870944","display_name":"Alexey Karpov","orcid":"https://orcid.org/0000-0003-3424-652X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Karpov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5207,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.94097094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2072","last_page":"2076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.7090592384338379},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6521479487419128},{"id":"https://openalex.org/keywords/breathing","display_name":"Breathing","score":0.5332096815109253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3997526168823242},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.10934162139892578}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090592384338379},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6521479487419128},{"id":"https://openalex.org/C39300077","wikidata":"https://www.wikidata.org/wiki/Q9530","display_name":"Breathing","level":2,"score":0.5332096815109253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3997526168823242},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.10934162139892578},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2666","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2666","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:dspace.library.uu.nl:1874/415580","is_oa":false,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/415580","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Contribution to conference"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1554944419","https://openalex.org/W1686810756","https://openalex.org/W2003304280","https://openalex.org/W2082927806","https://openalex.org/W2090777335","https://openalex.org/W2112739286","https://openalex.org/W2123237149","https://openalex.org/W2147768505","https://openalex.org/W2153379836","https://openalex.org/W2157331557","https://openalex.org/W2165698076","https://openalex.org/W2188183693","https://openalex.org/W2194775991","https://openalex.org/W2296199791","https://openalex.org/W2508457150","https://openalex.org/W2552884886","https://openalex.org/W2963194800","https://openalex.org/W2963614358","https://openalex.org/W2963946371","https://openalex.org/W2981810796","https://openalex.org/W3096396731"],"related_works":["https://openalex.org/W2312526371","https://openalex.org/W2109026862","https://openalex.org/W2119798006","https://openalex.org/W2963653539","https://openalex.org/W3017138616","https://openalex.org/W4239838734","https://openalex.org/W2393594734","https://openalex.org/W2967493086","https://openalex.org/W1547975896","https://openalex.org/W2954269264"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"deep":[3,39,99,170],"learning":[4,58,100,105],"approaches":[5],"for":[6,130],"the":[7,17,68,92,168,188],"Mask":[8,69],"and":[9,34,50,64,106,122,140,181],"Breathing":[10,93],"Sub-Challenges":[11],"(SCs),":[12],"which":[13],"are":[14],"addressed":[15],"by":[16,24],"INTERSPEECH":[18],"2020":[19],"Computational":[20],"Paralinguistics":[21],"Challenge.":[22],"Motivated":[23],"outstanding":[25],"performance":[26,157],"of":[27,37,158,167],"state-of-the-art":[28],"end-to-end":[29],"(E2E)":[30],"approaches,":[31],"we":[32,71,95,164],"explore":[33],"compare":[35],"effectiveness":[36],"different":[38],"Convolutional":[40],"Neural":[41],"Network":[42],"(CNN)":[43],"architectures":[44,78],"on":[45,79,88,114,118,143,177],"raw":[46,119],"data,":[47],"log":[48],"Mel-spectrograms,":[49],"Mel-Frequency":[51],"Cepstral":[52],"Coefficients.":[53],"We":[54],"apply":[55],"a":[56,144],"transfer":[57],"approach":[59],"to":[60,150],"improve":[61],"model\u2019s":[62],"efficiency":[63],"convergence":[65],"speed.":[66],"In":[67],"SC,":[70,94],"conduct":[72],"experiments":[73],"with":[74,125,137],"several":[75],"pretrained":[76,145],"CNN":[77,116,147],"log-Mel":[80,138],"spectrograms,":[81],"as":[82,84],"well":[83],"Support":[85],"Vector":[86],"Machines":[87],"baseline":[89],"features.":[90],"For":[91],"propose":[96],"an":[97],"ensemble":[98],"system":[101],"that":[102],"exploits":[103],"E2E":[104,110],"sequence":[107,131],"prediction.":[108],"The":[109,133],"model":[111,135,148],"is":[112,123,141],"based":[113,142],"1D":[115],"operating":[117],"speech":[120],"signals":[121],"coupled":[124],"Long":[126],"Short-Term":[127],"Memory":[128],"layers":[129],"modeling.":[132],"second":[134],"works":[136],"features":[139],"2D":[146],"stacked":[149],"Gated":[151],"Recurrent":[152],"Unit":[153],"layers.":[154],"To":[155],"increase":[156],"our":[159],"models":[160,172],"in":[161,193],"both":[162,194],"SCs,":[163],"use":[165],"ensembles":[166],"best":[169],"neural":[171],"obtained":[173],"from":[174],"N-fold":[175],"cross-validation":[176],"combined":[178],"challenge":[179,189],"training":[180],"development":[182],"datasets.":[183],"Our":[184],"results":[185],"markedly":[186],"outperform":[187],"test":[190],"set":[191],"baselines":[192],"SCs.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}