乐胖代购免代理版

{"id":"https://openalex.org/W3164680725","doi":"https://doi.org/10.1186/s13636-021-00208-5","title":"End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network","display_name":"End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network","publication_year":2021,"publication_date":"2021-05-12","ids":{"openalex":"https://openalex.org/W3164680725","doi":"https://doi.org/10.1186/s13636-021-00208-5","mag":"3164680725","pmid":"https://pubmed.ncbi.nlm.nih.gov/34721556","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/8550764"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00208-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00208-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00208-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060310242","display_name":"Duowei Tang","orcid":"https://orcid.org/0000-0003-3258-4728"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Duowei Tang","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001949402","display_name":"Peter Kuppens","orcid":"https://orcid.org/0000-0002-2363-2356"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Peter Kuppens","raw_affiliation_strings":["Faculty of Psychology and Educational Sciences, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Faculty of Psychology and Educational Sciences, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063634107","display_name":"Luc Geurts","orcid":"https://orcid.org/0000-0002-9608-9147"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Luc Geurts","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium","e-Media Research Lab, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"e-Media Research Lab, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073284331","display_name":"Toon van Waterschoot","orcid":"https://orcid.org/0000-0002-6323-7350"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Toon van Waterschoot","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing, and Data Analytics, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060310242"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367,"provenance":"doaj"},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367,"provenance":"doaj"},"fwci":3.795,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":24,"citation_normalized_percentile":{"value":0.863229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9977,"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":0.9969,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6585882},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6489838},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45165032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751688},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6585882},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6489838},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.63656783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.61628246},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.56952137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48601016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47983524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46999964},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45165032},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.44328246},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4162733},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1271725},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00208-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00208-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://doaj.org/article/315a03323bf244528ddd2af6d9455991","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://europepmc.org/articles/pmc8550764","pdf_url":"https://europepmc.org/articles/pmc8550764?pdf=render","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":["European Bioinformatics Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/675246","pdf_url":"https://lirias.kuleuven.be/bitstream/123456789/675246/2/21-85.pdf","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":["KU Leuven"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550764","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34721556","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":["National Institutes of Health"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-021-00208-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-021-00208-5","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_indexed_in_scopus":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[{"funder":"https://openalex.org/F4320322681","funder_display_name":"Onderzoeksraad, KU Leuven","award_id":"VES/19/004"},{"funder":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council","award_id":"201707650021"},{"funder":"https://openalex.org/F4320334678","funder_display_name":"European Research Council","award_id":"773268"}],"datasets":[],"versions":[],"referenced_works_count":48,"referenced_works":["https://openalex.org/W1849277567","https://openalex.org/W2005418748","https://openalex.org/W2037441721","https://openalex.org/W2045528981","https://openalex.org/W2047116924","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2122262023","https://openalex.org/W2134031328","https://openalex.org/W2146334809","https://openalex.org/W2150769028","https://openalex.org/W2157331557","https://openalex.org/W2158061940","https://openalex.org/W2165880886","https://openalex.org/W2194775991","https://openalex.org/W2239141610","https://openalex.org/W2313339984","https://openalex.org/W2346454595","https://openalex.org/W2399733683","https://openalex.org/W2610961739","https://openalex.org/W2626778328","https://openalex.org/W2648194195","https://openalex.org/W2747506362","https://openalex.org/W2747664154","https://openalex.org/W2784665486","https://openalex.org/W2792764867","https://openalex.org/W2808706139","https://openalex.org/W2885005742","https://openalex.org/W2888869035","https://openalex.org/W2889462515","https://openalex.org/W2890964092","https://openalex.org/W2892071465","https://openalex.org/W2915606245","https://openalex.org/W2937977583","https://openalex.org/W2940259008","https://openalex.org/W2949117887","https://openalex.org/W2949382160","https://openalex.org/W2951975883","https://openalex.org/W2962850830","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2966518489","https://openalex.org/W2973034847","https://openalex.org/W2973181312","https://openalex.org/W3021164770","https://openalex.org/W3113545796","https://openalex.org/W3179321675","https://openalex.org/W4541777"],"related_works":["https://openalex.org/W4375868962","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2964954556","https://openalex.org/W2942893872","https://openalex.org/W2530685530","https://openalex.org/W2088854863","https://openalex.org/W2065606036","https://openalex.org/W2011227383","https://openalex.org/W1976719989"],"abstract_inverted_index":{"Amongst":[0],"the":[1,8,15,19,45,63,73,90,103,113,123,141,156,163,186,193,200,215,234,241,251],"various":[2,219],"characteristics":[3,16],"of":[4,10,14,38,65,78,93,105,146,158,192,195,217,221,236,243],"a":[5,24,32,55,106,117,129,137,174,177],"speech":[6,26,47,260],"signal,":[7],"expression":[9],"emotion":[11,27,261],"is":[12,36,82,144],"one":[13],"that":[17,35,185,250],"exhibits":[18],"slowest":[20],"temporal":[21,42,149],"dynamics.":[22],"Hence,":[23],"performant":[25],"recognition":[28],"(SER)":[29],"system":[30],"requires":[31,189],"predictive":[33],"model":[34,75,114,143,165,188,196,253],"capable":[37,145],"learning":[39],"sufficiently":[40],"long":[41],"dependencies":[43,150],"in":[44,50,166,199],"analysed":[46],"signal.":[48],"Therefore,":[49],"this":[51],"work,":[52],"we":[53,248],"propose":[54],"novel":[56],"end-to-end":[57,179,238],"neural":[58,98],"network":[59,99],"architecture":[60],"based":[61],"on":[62],"concept":[64],"dilated":[66,108],"causal":[67,109],"convolution":[68,110],"with":[69,96,176],"context":[70,138],"stacking.":[71],"Firstly,":[72],"proposed":[74,142,164,187,252],"consists":[76],"only":[77,190],"parallelisable":[79],"layers":[80],"and":[81,169,172,231],"hence":[83,151],"suitable":[84],"for":[85],"parallel":[86],"processing,":[87],"while":[88,127,203],"avoiding":[89],"inherent":[91],"lack":[92],"parallelisability":[94],"occurring":[95],"recurrent":[97],"(RNN)":[100],"layers.":[101,160],"Secondly,":[102],"design":[104],"dedicated":[107],"block":[111],"allows":[112],"to":[115,155,213,232],"have":[116],"receptive":[118],"field":[119],"as":[120,122],"large":[121],"input":[124,222],"sequence":[125],"length,":[126],"maintaining":[128],"reasonably":[130],"low":[131],"computational":[132],"cost.":[133],"Thirdly,":[134],"by":[135],"introducing":[136],"stacking":[139],"structure,":[140],"exploiting":[147],"long-term":[148],"providing":[152],"an":[153,237],"alternative":[154],"use":[157,242],"RNN":[159],"We":[161],"evaluate":[162],"SER":[167,180,207],"regression":[168],"classification":[170],"tasks":[171],"provide":[173],"comparison":[175],"state-of-the-art":[178,201],"model.":[181],"Experimental":[182],"results":[183],"indicate":[184],"1/3":[191],"number":[194],"parameters":[197],"used":[198],"model,":[202],"also":[204],"significantly":[205],"improving":[206],"performance.":[208],"Further":[209],"experiments":[210],"are":[211],"reported":[212],"understand":[214],"impact":[216],"using":[218],"types":[220],"representations":[223],"(i.e.":[224],"raw":[225],"audio":[226,245],"samples":[227],"vs":[228],"log":[229],"mel-spectrograms)":[230],"illustrate":[233],"benefits":[235],"approach":[239],"over":[240],"hand-crafted":[244],"features.":[246],"Moreover,":[247],"show":[249],"can":[254],"efficiently":[255],"learn":[256],"intermediate":[257],"embeddings":[258],"preserving":[259],"information.":[262]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3164680725","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2025-01-17T04:37:49.015390","created_date":"2021-06-07"}