{"id":"https://openalex.org/W2995506319","doi":"https://doi.org/10.1109/acii.2019.8925496","title":"A Dual-Complementary Acoustic Embedding Network Learned from Raw Waveform for Speech Emotion Recognition","display_name":"A Dual-Complementary Acoustic Embedding Network Learned from Raw Waveform for Speech Emotion Recognition","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2995506319","doi":"https://doi.org/10.1109/acii.2019.8925496","mag":"2995506319"},"language":"en","primary_location":{"id":"doi:10.1109/acii.2019.8925496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2019.8925496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)","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/A5022951629","display_name":"Tzu\u2010Yun Huang","orcid":"https://orcid.org/0009-0008-0605-5826"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tzu-Yun Huang","raw_affiliation_strings":["Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001894880","display_name":"Jeng-Lin Li","orcid":"https://orcid.org/0000-0002-9261-1524"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeng-Lin Li","raw_affiliation_strings":["Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062975307","display_name":"Chun-Min Chang","orcid":"https://orcid.org/0000-0002-7603-9310"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Min Chang","raw_affiliation_strings":["Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086107623","display_name":"Chi-Chun Lee","orcid":"https://orcid.org/0000-0003-0186-4321"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chi-Chun Lee","raw_affiliation_strings":["Electrical Engineering, National Tsing Hua University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, National Tsing Hua University, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022951629"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.3838,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.68471837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"83","last_page":"88"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/waveform","display_name":"Waveform","score":0.8339933753013611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7211068868637085},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6629844307899475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6416184306144714},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5354748964309692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4874696731567383},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4786290228366852},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.441880464553833}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8339933753013611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211068868637085},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6629844307899475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6416184306144714},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5354748964309692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4874696731567383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4786290228366852},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.441880464553833},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acii.2019.8925496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acii.2019.8925496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 8th International Conference on Affective Computing and Intelligent Interaction (ACII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.75,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2080683407","https://openalex.org/W2090777335","https://openalex.org/W2110052520","https://openalex.org/W2110683152","https://openalex.org/W2111926505","https://openalex.org/W2114256784","https://openalex.org/W2120663682","https://openalex.org/W2146334809","https://openalex.org/W2181741066","https://openalex.org/W2239141610","https://openalex.org/W2602034649","https://openalex.org/W2610961739","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2774085128","https://openalex.org/W2889191742","https://openalex.org/W2889462515","https://openalex.org/W2897178676","https://openalex.org/W2962736520","https://openalex.org/W2963587715","https://openalex.org/W4239447739","https://openalex.org/W6676494506","https://openalex.org/W6746468907"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Speech":[0],"emotion":[1,121,135],"recognition":[2,18,26],"(SER)":[3],"technology":[4],"has":[5,15],"recently":[6],"become":[7],"a":[8,11,82,98,132],"trend":[9],"in":[10,131],"broader":[12],"field":[13],"and":[14,93],"achieved":[16],"remarkable":[17],"performances":[19,27],"using":[20,29],"deep":[21],"learning":[22,31],"technique.":[23],"However,":[24],"the":[25,106,125,142,155],"obtained":[28],"end-to-end":[30],"directly":[32],"from":[33,89,113],"raw":[34,51,77,94,107,144],"audio":[35],"waveform":[36,52,78,95,108,145],"still":[37],"hardly":[38],"exceed":[39],"those":[40],"based":[41],"on":[42,50,124],"hand-crafted":[43],"acoustic":[44,54,61,91],"descriptors.":[45],"Instead":[46],"of":[47,147,154],"solely":[48],"rely":[49],"or":[53],"descriptors":[55],"for":[56],"SER,":[57],"we":[58],"propose":[59],"an":[60,119],"space":[62],"augmentation":[63],"network,":[64],"termed":[65],"as":[66],"Dual-Complementary":[67],"Acoustic":[68],"Embedding":[69],"Network":[70],"(DCaEN),":[71],"that":[72,141],"combines":[73],"knowledge-based":[74],"features":[75],"with":[76,81],"embedding":[79,109,146],"learned":[80,143],"novel":[83],"complementary":[84],"constraint.":[85],"DCaEN":[86,148],"includes":[87],"representations":[88],"eGeMAPS":[90,157],"feature":[92],"by":[96],"specifying":[97],"negative":[99],"cosine":[100],"distance":[101],"loss":[102],"to":[103,110,151],"explicitly":[104],"constrain":[105],"be":[111],"different":[112],"eGeMAPS.":[114],"Our":[115,137],"experimental":[116],"results":[117],"demonstrate":[118],"improved":[120],"discriminative":[122],"power":[123],"IEMOCAP":[126],"database,":[127],"which":[128],"achieves":[129],"59.31%":[130],"four":[133],"class":[134],"recognition.":[136],"analysis":[138],"also":[139],"demonstrates":[140],"converges":[149],"close":[150],"reverse":[152],"mirroring":[153],"original":[156],"space.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}