{"id":"https://openalex.org/W3015964358","doi":"https://doi.org/10.1109/icassp40776.2020.9053039","title":"HGFM : A Hierarchical Grained and Feature Model for Acoustic Emotion Recognition","display_name":"HGFM : A Hierarchical Grained and Feature Model for Acoustic Emotion Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015964358","doi":"https://doi.org/10.1109/icassp40776.2020.9053039","mag":"3015964358"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100297939","display_name":"Yunfeng Xu","orcid":null},"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":"Yunfeng Xu","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086201515","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-7401-307X"},"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":"Hua Xu","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087498745","display_name":"Jiyun Zou","orcid":null},"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":"Jiyun Zou","raw_affiliation_strings":["State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Technology and Systems, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100297939"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.1085,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94762215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6499","last_page":"6503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.805479884147644},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7164677977561951},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6920233964920044},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6013240218162537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5642213821411133},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5243226289749146},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5203884840011597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4795243740081787},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4569840729236603},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44450142979621887},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43476688861846924},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41849613189697266},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4134073257446289},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2417370080947876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805479884147644},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7164677977561951},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6920233964920044},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6013240218162537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5642213821411133},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5243226289749146},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5203884840011597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4795243740081787},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4569840729236603},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44450142979621887},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43476688861846924},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41849613189697266},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4134073257446289},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2417370080947876},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/icassp40776.2020.9053039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1985867508","https://openalex.org/W2085662862","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2157331557","https://openalex.org/W2191779130","https://openalex.org/W2533262878","https://openalex.org/W2625297138","https://openalex.org/W2740550900","https://openalex.org/W2788776247","https://openalex.org/W2805662932","https://openalex.org/W2897403446","https://openalex.org/W2939362715","https://openalex.org/W2952307697","https://openalex.org/W2963686995","https://openalex.org/W2964230360","https://openalex.org/W2964300796","https://openalex.org/W6681409903","https://openalex.org/W6755541679","https://openalex.org/W6762073003"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W4388820305","https://openalex.org/W4221161909"],"abstract_inverted_index":{"To":[0],"solve":[1],"the":[2,35,68,74,81,97,110],"problem":[3],"of":[4,8,29,70,76,84],"poor":[5],"classification":[6],"performance":[7,112],"multiple":[9],"complex":[10],"emotions":[11],"in":[12],"acoustic":[13,30,62,82],"modalities,":[14],"we":[15,108],"propose":[16],"a":[17,42,51,59],"hierarchical":[18],"grained":[19],"and":[20,26,48,58,79,91,103,115],"feature":[21,63],"model":[22,40],"(HGFM).":[23],"The":[24,39],"frame-level":[25,43,71],"utterance-level":[27,52,77],"structures":[28],"samples":[31],"are":[32],"processed":[33],"by":[34],"recurrent":[36],"neural":[37],"network.":[38],"includes":[41],"representation":[44,53],"module":[45,54],"with":[46,55],"before":[47],"after":[49],"information,":[50,57],"context":[56],"different":[60],"level":[61],"fusion":[64],"module.":[65],"We":[66],"take":[67],"output":[69],"structure":[72,78],"as":[73],"input":[75],"extract":[80],"features":[83],"these":[85],"two":[86],"levels":[87],"respectively":[88],"for":[89],"effective":[90],"complementary":[92],"fusion.":[93],"Experiments":[94],"show":[95],"that":[96],"proposed":[98],"HGFM":[99],"has":[100],"better":[101],"accuracy":[102],"robustness.":[104],"By":[105],"this":[106],"method,":[107],"achieve":[109],"state-of-the-art":[111],"on":[113],"IEMOCAP":[114],"MELD":[116],"datasets.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}