{"id":"https://openalex.org/W2935991969","doi":"https://doi.org/10.1109/icsda.2018.8693020","title":"Multi-Modal Multi-Task Deep Learning For Speaker And Emotion Recognition Of TV-Series Data","display_name":"Multi-Modal Multi-Task Deep Learning For Speaker And Emotion Recognition Of TV-Series Data","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2935991969","doi":"https://doi.org/10.1109/icsda.2018.8693020","mag":"2935991969"},"language":"en","primary_location":{"id":"doi:10.1109/icsda.2018.8693020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2018.8693020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Oriental COCOSDA - International Conference on Speech Database and Assessments","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/A5048192694","display_name":"Sashi Novitasari","orcid":"https://orcid.org/0000-0001-7467-5682"},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Sashi Novitasari","raw_affiliation_strings":["Departement of Informatics, Bandung Institute of Technology, Indonesia"],"affiliations":[{"raw_affiliation_string":"Departement of Informatics, Bandung Institute of Technology, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102847246","display_name":"Quoc Truong","orcid":"https://orcid.org/0000-0003-1472-1370"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Quoc Truong Do","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109119353","display_name":"Dessi Puji Lestari","orcid":null},"institutions":[{"id":"https://openalex.org/I134635517","display_name":"Bandung Institute of Technology","ror":"https://ror.org/00apj8t60","country_code":"ID","type":"education","lineage":["https://openalex.org/I134635517"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Dessi Lestari","raw_affiliation_strings":["Departement of Informatics, Bandung Institute of Technology, Indonesia"],"affiliations":[{"raw_affiliation_string":"Departement of Informatics, Bandung Institute of Technology, Indonesia","institution_ids":["https://openalex.org/I134635517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048192694"],"corresponding_institution_ids":["https://openalex.org/I134635517"],"apc_list":null,"apc_paid":null,"fwci":0.4097,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69969621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.8104763031005859},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6733741760253906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6086204051971436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5903583765029907},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.552241861820221},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5143283605575562},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5043853521347046},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5012471675872803},{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.47378990054130554},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4614928960800171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45788490772247314},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4531540870666504},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4449698328971863},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.41026127338409424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3648383617401123},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08400988578796387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104763031005859},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6733741760253906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6086204051971436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5903583765029907},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.552241861820221},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5143283605575562},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5043853521347046},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5012471675872803},{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.47378990054130554},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4614928960800171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45788490772247314},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4531540870666504},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4449698328971863},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.41026127338409424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3648383617401123},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08400988578796387},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsda.2018.8693020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsda.2018.8693020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Oriental COCOSDA - International Conference on Speech Database and Assessments","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W1501669607","https://openalex.org/W1973378890","https://openalex.org/W1992810401","https://openalex.org/W2085662862","https://openalex.org/W2087110403","https://openalex.org/W2087748929","https://openalex.org/W2109135012","https://openalex.org/W2113396990","https://openalex.org/W2130162821","https://openalex.org/W2153579005","https://openalex.org/W2159094433","https://openalex.org/W2186965031","https://openalex.org/W2395639500","https://openalex.org/W2586291442","https://openalex.org/W2587024248","https://openalex.org/W2591183831","https://openalex.org/W2734403209","https://openalex.org/W2743915416","https://openalex.org/W2806843691","https://openalex.org/W2964128364","https://openalex.org/W2964243145","https://openalex.org/W4230277160","https://openalex.org/W4294170691","https://openalex.org/W6682691769","https://openalex.org/W6741274896"],"related_works":["https://openalex.org/W2938286185","https://openalex.org/W3126259644","https://openalex.org/W4352981569","https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2951125461","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W2546942002","https://openalex.org/W2563686518"],"abstract_inverted_index":{"Since":[0],"paralinguistic":[1],"aspects":[2],"must":[3],"be":[4],"considered":[5],"to":[6,19],"understand":[7],"speech,":[8],"we":[9,44],"construct":[10],"a":[11],"deep":[12],"learning":[13],"framework":[14],"that":[15,62],"utilizes":[16],"multi-modal":[17],"features":[18,40],"simultaneously":[20],"recognize":[21],"both":[22],"speakers":[23],"and":[24,35,52],"emotions.":[25],"There":[26],"are":[27],"three":[28,47],"kinds":[29],"of":[30],"feature":[31],"modalities:":[32],"acoustic,":[33],"lexical,":[34],"facial.":[36],"To":[37],"fuse":[38],"the":[39],"from":[41,59],"multiple":[42],"modalities,":[43],"experimented":[45],"on":[46],"methods:":[48],"majority":[49],"voting,":[50],"concatenation,":[51],"hierarchical":[53],"fusion.":[54],"The":[55],"recognition":[56],"was":[57],"done":[58],"TV-series":[60],"dataset":[61],"simulate":[63],"actual":[64],"conversations.":[65]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
