{"id":"https://openalex.org/W3192217872","doi":"https://doi.org/10.1145/3462244.3481003","title":"Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation","display_name":"Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3192217872","doi":"https://doi.org/10.1145/3462244.3481003","mag":"3192217872"},"language":"en","primary_location":{"id":"doi:10.1145/3462244.3481003","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3481003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.02510","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057823671","display_name":"Sarala Padi","orcid":"https://orcid.org/0000-0003-1139-6066"},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]},{"id":"https://openalex.org/I4210124755","display_name":"National Institute of Standards","ror":"https://ror.org/02zftm050","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210124755"]}],"countries":["EG","US"],"is_corresponding":true,"raw_author_name":"Sarala Padi","raw_affiliation_strings":["NIST, USA","National Institute of Standards and Technology"],"affiliations":[{"raw_affiliation_string":"NIST, USA","institution_ids":[]},{"raw_affiliation_string":"National Institute of Standards and Technology","institution_ids":["https://openalex.org/I4210124755","https://openalex.org/I1321296531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051167459","display_name":"Seyed Omid Sadjadi","orcid":null},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]},{"id":"https://openalex.org/I4210124755","display_name":"National Institute of Standards","ror":"https://ror.org/02zftm050","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210124755"]}],"countries":["EG","US"],"is_corresponding":false,"raw_author_name":"Seyed Omid Sadjadi","raw_affiliation_strings":["NIST, USA","National Institute of Standards and Technology"],"affiliations":[{"raw_affiliation_string":"NIST, USA","institution_ids":[]},{"raw_affiliation_string":"National Institute of Standards and Technology","institution_ids":["https://openalex.org/I4210124755","https://openalex.org/I1321296531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103196906","display_name":"Ram D. Sriram","orcid":null},"institutions":[{"id":"https://openalex.org/I1321296531","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416","country_code":"US","type":"funder","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065"]},{"id":"https://openalex.org/I4210124755","display_name":"National Institute of Standards","ror":"https://ror.org/02zftm050","country_code":"EG","type":"facility","lineage":["https://openalex.org/I4210124755"]}],"countries":["EG","US"],"is_corresponding":false,"raw_author_name":"Ram D. Sriram","raw_affiliation_strings":["NIST, USA","National Institute of Standards and Technology"],"affiliations":[{"raw_affiliation_string":"NIST, USA","institution_ids":[]},{"raw_affiliation_string":"National Institute of Standards and Technology","institution_ids":["https://openalex.org/I4210124755","https://openalex.org/I1321296531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["Computer Science and Electrical & Computer Engineering, University of Maryland, USA","University of Maryland - College Park"],"affiliations":[{"raw_affiliation_string":"Computer Science and Electrical & Computer Engineering, University of Maryland, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland - College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057823671"],"corresponding_institution_ids":["https://openalex.org/I1321296531","https://openalex.org/I4210124755"],"apc_list":null,"apc_paid":null,"fwci":0.1539,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43889672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"645","last_page":"652"},"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/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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/spectrogram","display_name":"Spectrogram","score":0.9210470914840698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532999515533447},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6938986778259277},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6782287359237671},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6618302464485168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6021744608879089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5658789277076721},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.49687960743904114},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47797510027885437},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4662180542945862},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4274655878543854},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.42324385046958923},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41876980662345886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4004899263381958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3471064865589142},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.23084795475006104},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08721068501472473},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08103296160697937}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9210470914840698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532999515533447},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6938986778259277},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6782287359237671},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6618302464485168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6021744608879089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5658789277076721},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.49687960743904114},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47797510027885437},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4662180542945862},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4274655878543854},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.42324385046958923},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41876980662345886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4004899263381958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3471064865589142},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.23084795475006104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08721068501472473},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08103296160697937},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3462244.3481003","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3462244.3481003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.02510","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02510","pdf_url":"https://arxiv.org/pdf/2108.02510","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2108.02510","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.02510","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3192217872","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.02510","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.02510","pdf_url":"https://arxiv.org/pdf/2108.02510","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3192217872.pdf","grobid_xml":"https://content.openalex.org/works/W3192217872.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1994458317","https://openalex.org/W2032254851","https://openalex.org/W2050752817","https://openalex.org/W2061068689","https://openalex.org/W2070960031","https://openalex.org/W2129120544","https://openalex.org/W2137639365","https://openalex.org/W2146334809","https://openalex.org/W2194775991","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2512449761","https://openalex.org/W2512885694","https://openalex.org/W2583743457","https://openalex.org/W2625297138","https://openalex.org/W2747664154","https://openalex.org/W2795986449","https://openalex.org/W2797947982","https://openalex.org/W2803098682","https://openalex.org/W2886300652","https://openalex.org/W2889191349","https://openalex.org/W2889191742","https://openalex.org/W2889462515","https://openalex.org/W2889544113","https://openalex.org/W2890964092","https://openalex.org/W2912728762","https://openalex.org/W2916297645","https://openalex.org/W2924116307","https://openalex.org/W2936451900","https://openalex.org/W2936774411","https://openalex.org/W2946073932","https://openalex.org/W2951442257","https://openalex.org/W2962736520","https://openalex.org/W2962770129","https://openalex.org/W2963130397","https://openalex.org/W2963467407","https://openalex.org/W2972498864","https://openalex.org/W2972640480","https://openalex.org/W2981087920","https://openalex.org/W2981461916","https://openalex.org/W2983165789","https://openalex.org/W2984211736","https://openalex.org/W3007708573","https://openalex.org/W3015707499","https://openalex.org/W3026006730","https://openalex.org/W3034924009","https://openalex.org/W3094335887","https://openalex.org/W3096147072","https://openalex.org/W3096723250","https://openalex.org/W3116195342","https://openalex.org/W3130293557","https://openalex.org/W3168191524","https://openalex.org/W4301204483"],"related_works":["https://openalex.org/W3207346153","https://openalex.org/W3097958944","https://openalex.org/W3144907487","https://openalex.org/W2970737019","https://openalex.org/W3134759918","https://openalex.org/W2785737646","https://openalex.org/W3197078573","https://openalex.org/W3034924009","https://openalex.org/W3113377686","https://openalex.org/W2982578033","https://openalex.org/W2586425531","https://openalex.org/W2305940569","https://openalex.org/W2963364041","https://openalex.org/W2999433375","https://openalex.org/W1495019370","https://openalex.org/W2963679184","https://openalex.org/W2963057973","https://openalex.org/W2524157061","https://openalex.org/W2978780389","https://openalex.org/W2936847140"],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"emotion":[2,45,149],"recognition":[3,85,150],"(SER)":[4],"is":[5,25,113],"a":[6,11,55,66,72,79,123],"challenging":[7],"task":[8],"that":[9,70,172],"plays":[10],"crucial":[12],"role":[13],"in":[14,23,116],"natural":[15],"human-computer":[16],"interaction.":[17],"One":[18],"of":[19,31,90,148,156],"the":[20,98,107,146,154,161,173,181],"main":[21],"challenges":[22],"SER":[24,117,182],"data":[26,34,131],"scarcity,":[27],"i.e.,":[28],"insufficient":[29],"amounts":[30,89],"carefully":[32],"labeled":[33],"to":[35,50,100,127,138,141],"build":[36],"and":[37,144,176,184],"fully":[38],"explore":[39],"complex":[40],"deep":[41],"learning":[42,57,68,175],"models":[43],"for":[44,109],"classification.":[46],"This":[47],"paper":[48],"aims":[49],"address":[51],"this":[52],"challenge":[53],"using":[54,87],"transfer":[56,67,174],"strategy":[58],"combined":[59,186],"with":[60],"spectrogram":[61,124,177],"augmentation.":[62],"Specifically,":[63],"we":[64,121],"propose":[65],"approach":[69,159],"leverages":[71],"pre-trained":[73],"residual":[74],"network":[75],"(ResNet)":[76],"model":[77,99],"including":[78],"statistics":[80,94],"pooling":[81,95],"layer":[82,96],"from":[83],"speaker":[84],"trained":[86],"large":[88],"speaker-labeled":[91],"data.":[92],"The":[93],"enables":[97],"efficiently":[101],"process":[102],"variable-length":[103],"input,":[104],"thereby":[105],"eliminating":[106],"need":[108],"sequence":[110],"truncation":[111],"which":[112],"commonly":[114],"used":[115],"systems.":[118],"In":[119],"addition,":[120],"adopt":[122],"augmentation":[125,178],"technique":[126],"generate":[128],"additional":[129],"training":[130],"samples":[132],"by":[133],"applying":[134],"random":[135],"time-frequency":[136],"masks":[137],"log-mel":[139],"spectrograms":[140],"mitigate":[142],"overfitting":[143],"improve":[145,180],"generalization":[147],"models.":[151],"We":[152],"evaluate":[153],"effectiveness":[155],"our":[157],"proposed":[158],"on":[160],"interactive":[162],"emotional":[163],"dyadic":[164],"motion":[165],"capture":[166],"(IEMOCAP)":[167],"dataset.":[168],"Experimental":[169],"results":[170],"indicate":[171],"approaches":[179],"performance,":[183],"when":[185],"achieve":[187],"state-of-the-art":[188],"results.":[189]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2025-10-10T00:00:00"}