{"id":"https://openalex.org/W3015953902","doi":"https://doi.org/10.1109/icassp40776.2020.9054621","title":"Deep Encoded Linguistic and Acoustic Cues for Attention Based End to End Speech Emotion Recognition","display_name":"Deep Encoded Linguistic and Acoustic Cues for Attention Based End to End Speech Emotion Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015953902","doi":"https://doi.org/10.1109/icassp40776.2020.9054621","mag":"3015953902"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054621","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/A5009006680","display_name":"Swapnil Bhosale","orcid":"https://orcid.org/0000-0001-8299-7569"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Swapnil Bhosale","raw_affiliation_strings":["TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077689139","display_name":"Rupayan Chakraborty","orcid":"https://orcid.org/0000-0002-3566-0784"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupayan Chakraborty","raw_affiliation_strings":["TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047383705","display_name":"Sunil Kumar Kopparapu","orcid":"https://orcid.org/0000-0002-0502-527X"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunil Kumar Kopparapu","raw_affiliation_strings":["TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research and Innovation \u2013 Mumbai, Tata Consultancy Services Ltd., INDIA","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2186,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91783116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7189","last_page":"7193"},"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7642119526863098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7002504467964172},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6205787062644958},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5212117433547974},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5125422477722168},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48075124621391296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4435335695743561},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.44281062483787537},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4301193058490753},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4240066707134247},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4185140132904053},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23284512758255005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642119526863098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7002504467964172},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6205787062644958},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5212117433547974},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5125422477722168},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48075124621391296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4435335695743561},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44281062483787537},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4301193058490753},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4240066707134247},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4185140132904053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23284512758255005},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/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":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054621","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":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W608122687","https://openalex.org/W1485005611","https://openalex.org/W2032254851","https://openalex.org/W2080576537","https://openalex.org/W2146334809","https://openalex.org/W2159836669","https://openalex.org/W2295001676","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2512449761","https://openalex.org/W2747664154","https://openalex.org/W2774085128","https://openalex.org/W2791213618","https://openalex.org/W2803098682","https://openalex.org/W2889191349","https://openalex.org/W2946794439","https://openalex.org/W2949889784","https://openalex.org/W2963403868","https://openalex.org/W2963587715","https://openalex.org/W2972314145","https://openalex.org/W2972602947","https://openalex.org/W4385245566","https://openalex.org/W6697498398","https://openalex.org/W6714031499","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W2184242386","https://openalex.org/W2325729322","https://openalex.org/W1923358586","https://openalex.org/W3126677997","https://openalex.org/W1610857240"],"abstract_inverted_index":{"An":[0],"End-to-End":[1],"model":[2],"with":[3,162],"convolutional":[4],"layers":[5,62],"and":[6,39,82,87,97,134,185],"multi-head":[7],"self":[8],"attention":[9],"mechanism":[10],"is":[11,74,155],"proposed":[12,122],"for":[13,90,151,175,181],"Speech":[14,67],"Emotion":[15],"Recognition":[16,68],"(SER)":[17],"task.":[18],"As":[19],"inputs,":[20],"we":[21,56,129,143],"propose":[22],"to":[23,116,157,172],"use":[24,57],"both":[25,80,85],"the":[26,33,40,51,60,72,110,118,126,139,146,158,167,176,182],"deep":[27,52],"encoded":[28],"linguistic":[29,53,83,164,168,193],"features":[30,148,169],"that":[31,43,145,190],"carry":[32],"language":[34],"related":[35],"context":[36],"of":[37,46,63,79,100,120],"emotion":[38,91],"audio":[41],"spectrogram":[42],"are":[44,114,170],"representatives":[45],"acoustic":[47,81,147],"cues.":[48],"To":[49,124],"facilitate":[50],"feature":[54],"representation,":[55],"outputs":[58],"from":[59],"intermediate":[61],"a":[64],"pre-trained":[65],"Automatic":[66],"(ASR)":[69],"model,":[70],"where":[71],"layer":[73],"selected":[75],"empirically.":[76],"The":[77],"influence":[78],"features,":[84],"separately":[86],"in":[88,93,160,195],"combination,":[89],"recognition":[92],"different":[94],"scenarios":[95],"(scripted":[96,184],"spontaneous":[98],"recording":[99],"emotional":[101],"speech":[102,161],"samples)":[103],"have":[104],"been":[105],"studied.":[106],"Extensive":[107],"experiments":[108],"on":[109],"standard":[111],"IEMOCAP":[112],"database":[113],"conducted":[115],"investigate":[117],"efficacy":[119],"our":[121],"approach.":[123],"address":[125],"class":[127],"imbalance,":[128],"carried":[130],"out":[131],"down":[132],"sampling":[133],"ensembling,":[135],"which":[136,154],"further":[137],"improved":[138],"SER":[140],"accuracy.":[141],"Overall,":[142],"observe":[144],"perform":[149],"best":[150],"improvised":[152,186],"recordings":[153,187],"due":[156],"spontaneity":[159],"less":[163],"correlation.":[165],"But":[166],"found":[171],"be":[173],"effective":[174],"scripted":[177],"as":[178,180],"well":[179],"combined":[183],"together)":[188],"scenario":[189],"reflects":[191],"more":[192],"information":[194],"spoken":[196],"utterances.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}