{"id":"https://openalex.org/W3162950882","doi":"https://doi.org/10.1109/icassp39728.2021.9413640","title":"MAEC: Multi-Instance Learning with an Adversarial Auto-Encoder-Based Classifier for Speech Emotion Recognition","display_name":"MAEC: Multi-Instance Learning with an Adversarial Auto-Encoder-Based Classifier for Speech Emotion Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162950882","doi":"https://doi.org/10.1109/icassp39728.2021.9413640","mag":"3162950882"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5085633547","display_name":"Changzeng Fu","orcid":"https://orcid.org/0000-0003-1083-9486"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Changzeng Fu","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Japan","Graduate School of Engineering Science, Osaka University, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101905297","display_name":"Chaoran Liu","orcid":"https://orcid.org/0000-0003-3789-2981"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chaoran Liu","raw_affiliation_strings":["Advanced Telecommunications Research Institute International,Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International,Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000037110","display_name":"Carlos Toshinori Ishi","orcid":"https://orcid.org/0000-0001-8130-1048"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Carlos Toshinori Ishi","raw_affiliation_strings":["Advanced Telecommunications Research Institute International,Japan","Advanced Telecommunications Research Institute International, Japan","Robotics Project, RIKEN, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Telecommunications Research Institute International,Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"Robotics Project, RIKEN, Japan","institution_ids":["https://openalex.org/I4210126580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101425832","display_name":"Hiroshi Ishiguro","orcid":"https://orcid.org/0000-0002-0805-7648"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Ishiguro","raw_affiliation_strings":["Osaka University,Graduate School of Engineering Science,Japan","Graduate School of Engineering Science, Osaka University, Japan","Advanced Telecommunications Research Institute International, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University,Graduate School of Engineering Science,Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Graduate School of Engineering Science, Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Advanced Telecommunications Research Institute International, Japan","institution_ids":["https://openalex.org/I4210104143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6299","last_page":"6303"},"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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":0.7587575316429138},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7515627145767212},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7251129150390625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6527383327484131},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6422252058982849},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5701219439506531},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.5039781928062439},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49531975388526917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4925912022590637},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4378000497817993},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.43440109491348267},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42602798342704773},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38195639848709106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33623868227005005},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3098987936973572}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587575316429138},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7515627145767212},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7251129150390625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527383327484131},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6422252058982849},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5701219439506531},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.5039781928062439},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49531975388526917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4925912022590637},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4378000497817993},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.43440109491348267},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42602798342704773},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38195639848709106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33623868227005005},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3098987936973572},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2029689100","https://openalex.org/W2064675550","https://openalex.org/W2074996852","https://openalex.org/W2085662862","https://openalex.org/W2105938655","https://openalex.org/W2146334809","https://openalex.org/W2153302588","https://openalex.org/W2156028525","https://openalex.org/W2541993698","https://openalex.org/W2735784269","https://openalex.org/W2939362715","https://openalex.org/W2939987519","https://openalex.org/W2959546144","https://openalex.org/W2963686995","https://openalex.org/W2964230360","https://openalex.org/W3015141382","https://openalex.org/W3015884429","https://openalex.org/W3081923735","https://openalex.org/W3097827011","https://openalex.org/W3104980021","https://openalex.org/W4293568373","https://openalex.org/W6682531405","https://openalex.org/W6755541679","https://openalex.org/W6762073003","https://openalex.org/W6775408604","https://openalex.org/W6780248173"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W3211393740","https://openalex.org/W3208049411","https://openalex.org/W3022908591","https://openalex.org/W2946768379","https://openalex.org/W2149903055","https://openalex.org/W1519613012"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,24],"propose":[4],"an":[5,44],"adversarial":[6],"auto-encoder-based":[7],"classifier,":[8],"which":[9],"can":[10],"regularize":[11],"the":[12,19,38,52,58,64,77,84],"distribution":[13],"of":[14,34],"latent":[15],"representation":[16],"to":[17,36],"smooth":[18],"boundaries":[20],"among":[21],"categories.":[22],"Moreover,":[23],"adopt":[25],"multi-instance":[26],"learning":[27],"by":[28],"dividing":[29],"speech":[30],"into":[31],"a":[32],"bag":[33],"segments":[35],"capture":[37],"most":[39],"salient":[40],"moments":[41],"for":[42],"presenting":[43],"emotion.":[45],"The":[46,69],"proposed":[47],"model":[48,75],"was":[49],"trained":[50],"on":[51,57,79,86],"IEMOCAP":[53],"dataset":[54],"and":[55,63,82],"evaluated":[56],"in-corpus":[59,80],"validation":[60,66,81,88],"set":[61,67],"(IEMOCAP)":[62],"cross-corpus":[65,87],"(MELD).":[68],"experiment":[70],"results":[71],"show":[72],"that":[73],"our":[74],"outperforms":[76],"baseline":[78],"increases":[83],"scores":[85],"with":[89],"regularization.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}