{"id":"https://openalex.org/W3011640397","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023347","title":"Adversarial Data Augmentation Network for Speech Emotion Recognition","display_name":"Adversarial Data Augmentation Network for Speech Emotion Recognition","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3011640397","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023347","mag":"3011640397"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5008845262","display_name":"Yi Lu","orcid":"https://orcid.org/0000-0002-4803-9305"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lu Yi","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008845262"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":3.483,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93850497,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"529","last_page":"534"},"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.836891770362854},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7696609497070312},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7060457468032837},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5983332991600037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5870198011398315},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5663977861404419},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5007920265197754},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.478566437959671},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45706573128700256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4123445749282837},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4084746837615967},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3867788314819336},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3584306836128235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836891770362854},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7696609497070312},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7060457468032837},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5983332991600037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5870198011398315},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5663977861404419},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5007920265197754},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.478566437959671},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45706573128700256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4123445749282837},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4084746837615967},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3867788314819336},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3584306836128235},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc47483.2019.9023347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W175750906","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W2009059481","https://openalex.org/W2050752817","https://openalex.org/W2090777335","https://openalex.org/W2099767163","https://openalex.org/W2146334809","https://openalex.org/W2148143831","https://openalex.org/W2165698076","https://openalex.org/W2168045655","https://openalex.org/W2187089797","https://openalex.org/W2295001676","https://openalex.org/W2296199791","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2512449761","https://openalex.org/W2625297138","https://openalex.org/W2739748921","https://openalex.org/W2770173563","https://openalex.org/W2786808285","https://openalex.org/W2885005742","https://openalex.org/W2889544113","https://openalex.org/W2962686539","https://openalex.org/W2963130397","https://openalex.org/W2964121744","https://openalex.org/W2964182121","https://openalex.org/W4318977982","https://openalex.org/W4320013936","https://openalex.org/W6605980550","https://openalex.org/W6607193717","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6697151493","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6741832134","https://openalex.org/W6760563260","https://openalex.org/W6780248173"],"related_works":["https://openalex.org/W2995777218","https://openalex.org/W4293320219","https://openalex.org/W2953246223","https://openalex.org/W4283584549","https://openalex.org/W2554314924","https://openalex.org/W4288256692","https://openalex.org/W2998859928","https://openalex.org/W4381885966","https://openalex.org/W2969399009","https://openalex.org/W4398186750"],"abstract_inverted_index":{"Insufficient":[0],"data":[1,19,33,95,128],"is":[2],"a":[3,23,46,144],"common":[4,104],"issue":[5],"in":[6],"training":[7],"deep":[8],"learning":[9],"models.":[10],"With":[11],"the":[12,52,55,59,63,66,69,78,81,84,87,108,123],"introduction":[13],"of":[14,62,68,83],"generative":[15],"adversarial":[16,94],"networks":[17],"(GANs),":[18],"augmentation":[20,34,96],"has":[21],"become":[22],"promising":[24],"solution":[25],"to":[26,54,147],"this":[27],"problem.":[28],"This":[29],"paper":[30],"investigates":[31],"whether":[32],"can":[35,74,99,125],"help":[36],"improve":[37],"speech":[38],"emotion":[39],"recognition.":[40],"Unlike":[41],"conventional":[42],"GANs,":[43],"we":[44],"train":[45],"GAN":[47],"with":[48,107,139],"an":[49,131,136],"autoencoder,":[50],"where":[51],"input":[53],"discriminator":[56],"comes":[57],"from":[58,77],"bottleneck":[60],"layer":[61],"autoencoder":[64],"and":[65,114,142],"output":[67,82],"generator.":[70],"The":[71,90],"synthetic":[72],"samples":[73,101],"be":[75],"obtained":[76],"decoder,":[79],"using":[80,118],"generator":[85],"as":[86,121],"decoder's":[88],"input.":[89],"combined":[91],"network,":[92],"namely":[93],"network":[97],"(ADAN),":[98],"generate":[100],"that":[102,117,129],"share":[103],"latent":[105],"representation":[106],"real":[109],"data.":[110],"Evaluations":[111],"on":[112],"EmoDB":[113],"IEMOCAP":[115],"show":[116],"OpenSmile":[119],"features":[120],"input,":[122],"ADAN":[124],"produce":[126],"augmented":[127],"make":[130,143],"ordinary":[132],"SVM":[133],"classifier":[134,138],"outperforms":[135],"RNN":[137],"local":[140],"attention":[141],"DNN":[145],"competitive":[146],"some":[148],"state-of-the":[149],"art":[150],"systems.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}