{"id":"https://openalex.org/W2889374687","doi":"https://doi.org/10.21437/interspeech.2018-1242","title":"An Attention Pooling Based Representation Learning Method for Speech Emotion Recognition","display_name":"An Attention Pooling Based Representation Learning Method for Speech Emotion Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889374687","doi":"https://doi.org/10.21437/interspeech.2018-1242","mag":"2889374687"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1242","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5100432309","display_name":"Pengcheng Li","orcid":"https://orcid.org/0000-0002-1183-1470"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Li","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]},{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["School of Computing, University of Kent, Medway, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Kent, Medway, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":186,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3087","last_page":"3091"},"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":0.9987000226974487,"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":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.7933958768844604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.771203339099884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7424778938293457},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6854047775268555},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5505439043045044},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4974253475666046},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4495667815208435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42292702198028564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3279593586921692}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7933958768844604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771203339099884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7424778938293457},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6854047775268555},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5505439043045044},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4974253475666046},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4495667815208435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42292702198028564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3279593586921692},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1242","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:67453","is_oa":false,"landing_page_url":"https://doi.org/10.21437/Interspeech.2018-1242>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1542637018","https://openalex.org/W1836465849","https://openalex.org/W2087618018","https://openalex.org/W2087750470","https://openalex.org/W2097117768","https://openalex.org/W2104657103","https://openalex.org/W2108581428","https://openalex.org/W2131537280","https://openalex.org/W2145227859","https://openalex.org/W2146334809","https://openalex.org/W2150341604","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2396144419","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2515667479","https://openalex.org/W2622203030","https://openalex.org/W2625297138","https://openalex.org/W2648194195","https://openalex.org/W2707551695","https://openalex.org/W2729172879","https://openalex.org/W2747664154","https://openalex.org/W2752386593","https://openalex.org/W2899771611","https://openalex.org/W2949117887","https://openalex.org/W2962736520","https://openalex.org/W4205947740"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W147410782","https://openalex.org/W4287804464","https://openalex.org/W3022252430","https://openalex.org/W3103989898","https://openalex.org/W2152352598","https://openalex.org/W3126677997","https://openalex.org/W3204853141"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,21],"attention":[4,87,106,116],"pooling":[5,88,97,107],"based":[6],"representation":[7,17],"learning":[8],"method":[9,89,156],"for":[10,161,165],"speech":[11,37],"emotion":[12],"recognition":[13,137],"(SER).":[14],"The":[15,67],"emotional":[16,83],"is":[18,90],"learned":[19,68],"in":[20],"end-to-end":[22],"fashion":[23],"by":[24,40,157],"applying":[25],"a":[26,85,136],"deep":[27],"convolutional":[28,77],"neural":[29],"network":[30],"(CNN)":[31],"directly":[32],"to":[33,54,126],"spectrograms":[34],"extracted":[35],"from":[36,63],"utterances.":[38],"Motivated":[39],"the":[41,64,75,81,95,104,128,131,154],"success":[42],"of":[43,47,130,139],"GoogleNet,":[44],"two":[45],"groups":[46],"filters":[48],"with":[49,94],"different":[50],"shapes":[51],"are":[52,70],"designed":[53],"capture":[55],"both":[56],"temporal":[57],"and":[58,72,102,113,144,163],"frequency":[59],"domain":[60],"context":[61],"information":[62],"input":[65],"spectrogram.":[66],"features":[69],"concatenated":[71],"fed":[73],"into":[74],"subsequent":[76],"layers.":[78],"To":[79],"learn":[80],"final":[82],"representation,":[84],"novel":[86],"further":[91],"proposed.":[92],"Compared":[93],"existing":[96],"methods,":[98],"such":[99],"as":[100],"max-pooling":[101],"average-pooling,":[103],"proposed":[105,132],"can":[108],"effectively":[109],"incorporate":[110],"class-agnostic":[111],"bottom-up,":[112],"class-specific":[114],"top-down,":[115],"maps.":[117],"We":[118],"conduct":[119],"extensive":[120],"evaluations":[121],"on":[122],"benchmark":[123],"IEMOCAP":[124],"data":[125],"assess":[127],"effectiveness":[129],"representation.":[133],"Results":[134],"demonstrate":[135],"performance":[138],"71.8%":[140],"weighted":[141],"accuracy":[142,147],"(WA)":[143],"68%":[145],"unweighted":[146],"(UA)":[148],"over":[149],"four":[150],"emotions,":[151],"which":[152],"outperforms":[153],"state-of-the-art":[155],"about":[158],"3%":[159],"absolute":[160],"WA":[162],"4%":[164],"UA.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":34},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":24}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}