{"id":"https://openalex.org/W2765998482","doi":"https://doi.org/10.1145/3123266.3123353","title":"Deep Temporal Models using Identity Skip-Connections for Speech Emotion Recognition","display_name":"Deep Temporal Models using Identity Skip-Connections for Speech Emotion Recognition","publication_year":2017,"publication_date":"2017-10-19","ids":{"openalex":"https://openalex.org/W2765998482","doi":"https://doi.org/10.1145/3123266.3123353","mag":"2765998482"},"language":"en","primary_location":{"id":"doi:10.1145/3123266.3123353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","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/A5010496535","display_name":"Jaebok Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Jaebok Kim","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074888054","display_name":"Gwenn Englebienne","orcid":"https://orcid.org/0000-0002-3130-2082"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Gwenn Englebienne","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068294985","display_name":"Khiet P. Truong","orcid":"https://orcid.org/0000-0002-7243-0523"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Khiet P. Truong","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077237173","display_name":"Vanessa Evers","orcid":"https://orcid.org/0000-0002-5650-2830"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vanessa Evers","raw_affiliation_strings":["University of Twente, Enschede, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9218,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94840999,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055524826049805},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6459968686103821},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6422849893569946},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5604441165924072},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5246860384941101},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5012760162353516},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.49749234318733215},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48421359062194824},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.46073171496391296},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4344373941421509},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4272419810295105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4212256073951721},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4178144335746765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3995688855648041},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38909533619880676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33962976932525635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1437300145626068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08013004064559937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055524826049805},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6459968686103821},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6422849893569946},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5604441165924072},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5246860384941101},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5012760162353516},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.49749234318733215},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48421359062194824},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46073171496391296},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4344373941421509},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4272419810295105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4212256073951721},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4178144335746765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3995688855648041},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38909533619880676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33962976932525635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1437300145626068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08013004064559937},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3123266.3123353","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3123266.3123353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/93386b45-9a53-47b2-ba4f-80298bb244a0","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/93386b45-9a53-47b2-ba4f-80298bb244a0","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","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":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kim, J, Englebienne, G, Truong, K P & Evers, V 2017, Deep Temporal Models using Identity Skip-Connections for Speech Emotion Recognition. in MM '17 : Proceedings of the 2017 ACM on Multimedia Conference. Association for Computing Machinery, pp. 1006-1013, 25th ACM Multimedia Conference, MM 2017, Mountain View, California, United States, 23/10/17. https://doi.org/10.1145/3123266.3123353","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W100428360","https://openalex.org/W175750906","https://openalex.org/W1581984155","https://openalex.org/W1600744878","https://openalex.org/W1847088711","https://openalex.org/W2016043834","https://openalex.org/W2024289965","https://openalex.org/W2064675550","https://openalex.org/W2087618018","https://openalex.org/W2093174546","https://openalex.org/W2095705004","https://openalex.org/W2099215977","https://openalex.org/W2114025269","https://openalex.org/W2125462608","https://openalex.org/W2135776491","https://openalex.org/W2137639365","https://openalex.org/W2146334809","https://openalex.org/W2155063211","https://openalex.org/W2163922914","https://openalex.org/W2168692779","https://openalex.org/W2181741066","https://openalex.org/W2194775991","https://openalex.org/W2232901134","https://openalex.org/W2274801302","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2473934411","https://openalex.org/W2512449761","https://openalex.org/W2561907692","https://openalex.org/W2963268748","https://openalex.org/W2963410064","https://openalex.org/W2964084166","https://openalex.org/W2964128364","https://openalex.org/W4213124581"],"related_works":["https://openalex.org/W3196952692","https://openalex.org/W2984708981","https://openalex.org/W2755231872","https://openalex.org/W4300939921","https://openalex.org/W2972212393","https://openalex.org/W4383097772","https://openalex.org/W2964350391","https://openalex.org/W2274287116","https://openalex.org/W2897517148","https://openalex.org/W2983358626"],"abstract_inverted_index":{"Deep":[0],"architectures":[1,59],"using":[2],"identity":[3,20,45],"skip-connections":[4,21,46,82,140,149],"have":[5],"demonstrated":[6],"groundbreaking":[7],"performance":[8],"in":[9,106,127],"the":[10,42,48,113],"field":[11],"of":[12,25,44,50,96,125,141],"image":[13],"classification.":[14],"Recently,":[15],"empirical":[16],"studies":[17],"suggested":[18],"that":[19,29,147],"enable":[22],"ensemble-like":[23],"behaviour":[24],"shallow":[26],"networks,":[27],"and":[28,76,83,98,120,145],"depth":[30],"is":[31,90,99],"not":[32],"a":[33,68,84,136],"solo":[34],"ingredient":[35],"for":[36,47],"their":[37],"success.":[38],"Therefore,":[39],"we":[40,66,134],"examine":[41,135],"potential":[43],"task":[49],"Speech":[51],"Emotion":[52],"Recognition":[53],"(SER)":[54],"where":[55],"moderately":[56],"deep":[57],"temporal":[58],"are":[60,150],"often":[61],"employed.":[62],"To":[63],"this":[64],"end,":[65],"propose":[67],"novel":[69],"architecture":[70,89,111],"which":[71],"regulates":[72],"unimpeded":[73],"feature":[74],"flows":[75],"captures":[77],"long-term":[78],"dependencies":[79],"via":[80],"gate-based":[81,148],"memory":[85],"mechanism.":[86],"Our":[87,109],"proposed":[88,110],"compared":[91],"to":[92],"other":[93],"state-of-the-art":[94,114],"methods":[95,115],"SER":[97],"evaluated":[100],"on":[101],"large":[102],"aggregated":[103],"corpora":[104],"recorded":[105],"different":[107],"contexts.":[108],"outperforms":[112],"by":[116],"9":[117],"-":[118],"15%":[119],"achieves":[121],"an":[122,128],"Unweighted":[123],"Accuracy":[124],"80.5%":[126],"imbalanced":[129],"class":[130],"distribution.":[131],"In":[132],"addition,":[133],"variant":[137],"adopting":[138],"simplified":[139,154],"Residual":[142],"Networks":[143],"(ResNet)":[144],"show":[146],"more":[151],"effective":[152],"than":[153],"skip-connections.":[155]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}