{"id":"https://openalex.org/W4372263296","doi":"https://doi.org/10.1109/icassp49357.2023.10095588","title":"Speech Emotion Recognition Via Two-Stream Pooling Attention With Discriminative Channel Weighting","display_name":"Speech Emotion Recognition Via Two-Stream Pooling Attention With Discriminative Channel Weighting","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372263296","doi":"https://doi.org/10.1109/icassp49357.2023.10095588"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100349835","display_name":"Ke Liu","orcid":"https://orcid.org/0000-0001-8151-4326"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Liu","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055174340","display_name":"Dekui Wang","orcid":"https://orcid.org/0000-0003-4783-446X"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dekui Wang","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076984427","display_name":"Dongya Wu","orcid":"https://orcid.org/0000-0002-2310-3243"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongya Wu","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002937692","display_name":"Jun Feng","orcid":"https://orcid.org/0000-0001-9917-1819"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Feng","raw_affiliation_strings":["Northwest University,School of Information Science and Technology,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwest University,School of Information Science and Technology,Xi’an,China","institution_ids":["https://openalex.org/I37802460"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37802460"],"apc_list":null,"apc_paid":null,"fwci":1.9333,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88870665,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9983999729156494,"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/discriminative-model","display_name":"Discriminative model","score":0.8977851271629333},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.8111681938171387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7209902405738831},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6680029034614563},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.582085132598877},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5806613564491272},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.559760332107544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.557180643081665},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5455673336982727},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5429465770721436},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48626697063446045},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44196394085884094},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.43883028626441956},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.323000431060791},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20740795135498047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1230529248714447}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8977851271629333},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8111681938171387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7209902405738831},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6680029034614563},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.582085132598877},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5806613564491272},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.559760332107544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.557180643081665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5455673336982727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5429465770721436},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48626697063446045},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44196394085884094},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.43883028626441956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.323000431060791},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20740795135498047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1230529248714447},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2016896048","https://openalex.org/W2043929537","https://openalex.org/W2146334809","https://openalex.org/W2187089797","https://openalex.org/W2739444023","https://openalex.org/W2792643794","https://openalex.org/W2885005742","https://openalex.org/W2891488835","https://openalex.org/W2908510526","https://openalex.org/W2973181312","https://openalex.org/W2998674125","https://openalex.org/W3005916310","https://openalex.org/W3015489952","https://openalex.org/W3036601975","https://openalex.org/W3095789936","https://openalex.org/W3126560186","https://openalex.org/W3160039712","https://openalex.org/W3162475537","https://openalex.org/W3197642003","https://openalex.org/W3215440557","https://openalex.org/W4205383840","https://openalex.org/W4221162872","https://openalex.org/W4293519468","https://openalex.org/W4295312788","https://openalex.org/W6638444622","https://openalex.org/W6749029207","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6780218876","https://openalex.org/W6790202116"],"related_works":["https://openalex.org/W2729514902","https://openalex.org/W2024160000","https://openalex.org/W2773500201","https://openalex.org/W2061273563","https://openalex.org/W2970216048","https://openalex.org/W2285052147","https://openalex.org/W2043075591","https://openalex.org/W2806866760","https://openalex.org/W2546942002","https://openalex.org/W4386303287"],"abstract_inverted_index":{"Multi-view":[0],"Speech":[1],"Emotion":[2],"Recognition":[3],"(SER)":[4],"based":[5,101],"on":[6,22,102,130],"the":[7,17,60,64,110,124],"pre-trained":[8],"model":[9],"has":[10,127],"achieved":[11],"success":[12],"in":[13],"speaker-independent":[14,132],"scenarios.":[15],"However,":[16],"existing":[18],"SER":[19,111],"methods":[20],"rely":[21],"excessive":[23],"feature":[24,29,47],"views":[25],"and":[26],"have":[27],"complicated":[28],"fusion":[30,99],"strategies.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,50],"propose":[36],"a":[37,52,68,85],"novel":[38],"method":[39,126],"to":[40,58,94],"learn":[41],"effective":[42],"emotion-related":[43],"information":[44],"from":[45],"two":[46,96,131],"views.":[48],"First,":[49],"present":[51],"Discriminative":[53],"Channel":[54],"Weighting":[55],"(DCW)":[56],"module":[57,75],"weight":[59],"channel":[61,82],"dimension":[62],"of":[63,70,80,98,123],"features":[65,100],"produced":[66],"by":[67,115],"set":[69],"multi-scale":[71],"convolution":[72],"layers.":[73,120],"This":[74],"allows":[76],"for":[77],"discriminative":[78],"weighting":[79],"complex":[81],"dimensions.":[83],"Second,":[84],"concise":[86],"Two-stream":[87],"Pooling":[88],"Attention":[89],"(TsPA)":[90],"strategy":[91],"is":[92,113],"proposed":[93,125],"generate":[95],"groups":[97],"different":[103,107],"channel-level":[104],"embeddings":[105],"with":[106],"emphasis.":[108],"Finally,":[109],"task":[112],"completed":[114],"three":[116],"consecutive":[117],"fully":[118],"connected":[119],"The":[121],"effectiveness":[122],"been":[128],"demonstrated":[129],"validation":[133],"strategies,":[134],"outperforming":[135],"other":[136],"state-of-the-art":[137],"approaches.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}