{"id":"https://openalex.org/W2936372954","doi":"https://doi.org/10.1109/icassp.2019.8683765","title":"Learning Discriminative Features from Spectrograms Using Center Loss for Speech Emotion Recognition","display_name":"Learning Discriminative Features from Spectrograms Using Center Loss for Speech Emotion Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936372954","doi":"https://doi.org/10.1109/icassp.2019.8683765","mag":"2936372954"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5052785114","display_name":"Dongyang Dai","orcid":"https://orcid.org/0000-0001-5811-5781"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongyang Dai","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667025","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0002-6527-5502"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102903512","display_name":"Runnan Li","orcid":"https://orcid.org/0000-0002-0922-003X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runnan Li","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixin Wu","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua National Laboratory for Information Science and Technology (TNList), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052785114"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.9002,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97045268,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"2019","issue":null,"first_page":"7405","last_page":"7409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987999796867371,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9987999796867371,"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/spectrogram","display_name":"Spectrogram","score":0.9635965824127197},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8776540160179138},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7081043720245361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6602983474731445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5678750276565552},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5645599365234375},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5530246496200562},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.44376474618911743},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4204613268375397},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4178921580314636},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.2943613529205322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1667804718017578},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.13129815459251404}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9635965824127197},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8776540160179138},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7081043720245361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6602983474731445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5678750276565552},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5645599365234375},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5530246496200562},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.44376474618911743},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4204613268375397},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4178921580314636},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2943613529205322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1667804718017578},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.13129815459251404},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683765","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683765","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"mag:3037604809","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902249318796851","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W2074788634","https://openalex.org/W2096733369","https://openalex.org/W2146334809","https://openalex.org/W2157331557","https://openalex.org/W2163922914","https://openalex.org/W2170876097","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2395587375","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2520774990","https://openalex.org/W2747664154","https://openalex.org/W2781987798","https://openalex.org/W2889065492","https://openalex.org/W2919115771","https://openalex.org/W2964121744","https://openalex.org/W3099206234","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6683258052","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6726946684","https://openalex.org/W6747603630"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3210733254"],"abstract_inverted_index":{"Identifying":[0],"the":[1,9,13,16,72,76,85,89,110,118],"emotional":[2],"state":[3],"from":[4,40,62],"speech":[5],"is":[6,25],"essential":[7],"for":[8,22,44,104],"natural":[10],"interaction":[11],"of":[12],"machine":[14],"with":[15],"speaker.":[17],"However,":[18],"extracting":[19],"effective":[20,102],"features":[21,39,61,73,103],"emotion":[23,45,64,78,105],"recognition":[24,46],"difficult,":[26],"as":[27],"emotions":[28],"are":[29,124],"ambiguous.":[30],"We":[31],"propose":[32],"a":[33],"novel":[34],"approach":[35],"to":[36,75,80,98],"learn":[37],"discriminative":[38,90],"variable":[41],"length":[42],"spectrograms":[43],"by":[47,109,126],"cooperating":[48],"soft-max":[49,57],"cross-entropy":[50,58],"loss":[51,54,59,69],"and":[52,67,121,132],"center":[53,68,115],"together.":[55],"The":[56],"enables":[60],"different":[63],"categories":[65],"separable,":[66],"efficiently":[70],"pulls":[71],"belonging":[74],"same":[77],"category":[79],"their":[81],"center.":[82],"By":[83],"combining":[84],"two":[86],"losses":[87],"together,":[88],"power":[91],"will":[92],"be":[93],"highly":[94],"enhanced,":[95],"which":[96],"leads":[97],"network":[99],"learning":[100],"more":[101,133],"recognition.":[106],"As":[107],"demonstrated":[108],"experimental":[111],"results,":[112],"after":[113],"introducing":[114],"loss,":[116],"both":[117],"unweighted":[119],"accuracy":[120,123],"weighted":[122],"improved":[125],"over":[127],"3%":[128],"on":[129,136],"Mel-spectrogram":[130],"input,":[131],"than":[134],"4%":[135],"Short":[137],"Time":[138],"Fourier":[139],"Transform":[140],"spectrogram":[141],"input.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}