{"id":"https://openalex.org/W3161565210","doi":"https://doi.org/10.1109/icpr48806.2021.9413144","title":"End-to-end Triplet Loss based Emotion Embedding System for Speech Emotion Recognition","display_name":"End-to-end Triplet Loss based Emotion Embedding System for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3161565210","doi":"https://doi.org/10.1109/icpr48806.2021.9413144","mag":"3161565210"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5044412028","display_name":"Puneet Kumar","orcid":"https://orcid.org/0000-0002-4318-1353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Puneet Kumar","raw_affiliation_strings":["Indian Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101112505","display_name":"Sidharth Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sidharth Jain","raw_affiliation_strings":["Indian Institute of Technology, Roorkee, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Roorkee, India","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030765476","display_name":"Balasubramanian Raman","orcid":"https://orcid.org/0000-0001-6277-6267"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balasubramanian Raman","raw_affiliation_strings":["Indian Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036208317","display_name":"Partha Pratim Roy","orcid":"https://orcid.org/0000-0002-5735-5254"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Partha Pratim Roy","raw_affiliation_strings":["Indian Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066589561","display_name":"Masakazu Iwamura","orcid":"https://orcid.org/0000-0003-2508-2869"},"institutions":[{"id":"https://openalex.org/I15807432","display_name":"Osaka Prefecture University","ror":"https://ror.org/02cf1je33","country_code":"JP","type":"education","lineage":["https://openalex.org/I15807432"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakazu Iwamura","raw_affiliation_strings":["Osaka Prefecture University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka Prefecture University, Japan","institution_ids":["https://openalex.org/I15807432"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8766","last_page":"8773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8782469630241394},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8122450113296509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6612983345985413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6432051658630371},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4800318777561188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4634179174900055},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.45836174488067627},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43221622705459595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3445468246936798},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20194196701049805}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8782469630241394},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8122450113296509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6612983345985413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6432051658630371},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4800318777561188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634179174900055},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.45836174488067627},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43221622705459595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3445468246936798},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20194196701049805}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W58337816","https://openalex.org/W1993267429","https://openalex.org/W2043152858","https://openalex.org/W2074788634","https://openalex.org/W2087618018","https://openalex.org/W2096733369","https://openalex.org/W2099767163","https://openalex.org/W2102953093","https://openalex.org/W2146334809","https://openalex.org/W2155986100","https://openalex.org/W2156503193","https://openalex.org/W2189018360","https://openalex.org/W2194775991","https://openalex.org/W2612434969","https://openalex.org/W2648194195","https://openalex.org/W2765998482","https://openalex.org/W2803187616","https://openalex.org/W2805662932","https://openalex.org/W2887729140","https://openalex.org/W2889494795","https://openalex.org/W2889717020","https://openalex.org/W2891359673","https://openalex.org/W2909354520","https://openalex.org/W2919115771","https://openalex.org/W2963702081","https://openalex.org/W2963759070","https://openalex.org/W2964300796","https://openalex.org/W2964370293","https://openalex.org/W3008039831","https://openalex.org/W3008130537","https://openalex.org/W3015707499","https://openalex.org/W3099206234","https://openalex.org/W6737575990","https://openalex.org/W6751420435","https://openalex.org/W6754415674","https://openalex.org/W6773986906"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W3005627584","https://openalex.org/W3170224572"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"an":[3],"end-to-end":[4],"neural":[5],"embedding":[6,78,89,92],"system":[7,24,55,130],"based":[8],"on":[9],"triplet":[10,68],"loss":[11,69],"and":[12,67,77,102,134,142],"residual":[13],"learning":[14],"has":[15,131],"been":[16],"proposed":[17,23,54,129],"for":[18,140],"speech":[19,34,48,121],"emotion":[20,126],"recognition.":[21],"The":[22,36,53,71,91,128],"learns":[25],"the":[26,29,33,43,74,81,88,103,110],"embeddings":[27,38],"from":[28],"emotional":[30],"information":[31],"of":[32,50,80,94],"utterances.":[35],"learned":[37],"are":[39,84,97,107,115],"used":[40,85],"to":[41,86,117],"recognize":[42],"emotions":[44,96,139],"portrayed":[45],"by":[46],"given":[47],"samples":[49],"various":[51,95],"lengths.":[52],"implements":[56],"Residual":[57],"Neural":[58],"Network":[59],"architecture.":[60],"It":[61],"is":[62],"trained":[63,82],"using":[64,109],"softmax":[65],"pretraining":[66],"function.":[70],"weights":[72],"between":[73],"fully":[75],"connected":[76],"layers":[79],"network":[83],"calculate":[87],"values.":[90],"representations":[93],"mapped":[98],"onto":[99],"a":[100,119],"hyperplane,":[101],"angles":[104,114],"among":[105],"them":[106],"computed":[108],"cosine":[111],"similarity.":[112],"These":[113],"utilized":[116],"classify":[118],"new":[120],"sample":[122],"into":[123],"its":[124],"appropriate":[125],"class.":[127],"demonstrated":[132],"91.67%":[133],"64.44%":[135],"accuracy":[136],"while":[137],"recognizing":[138],"RAVDESS":[141],"IEMOCAP":[143],"dataset,":[144],"respectively.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}