{"id":"https://openalex.org/W4372259935","doi":"https://doi.org/10.1109/icassp49357.2023.10095892","title":"Towards Learning Emotion Information from Short Segments of Speech","display_name":"Towards Learning Emotion Information from Short Segments of Speech","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259935","doi":"https://doi.org/10.1109/icassp49357.2023.10095892"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5003220837","display_name":"Tilak Purohit","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tilak Purohit","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000317921","display_name":"Sarthak Yadav","orcid":"https://orcid.org/0000-0002-1979-9460"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sarthak Yadav","raw_affiliation_strings":["Aalborg University,Denmark","Aalborg University, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg University,Denmark","institution_ids":["https://openalex.org/I891191580"]},{"raw_affiliation_string":"Aalborg University, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087200921","display_name":"Bogdan Vlasenko","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Bogdan Vlasenko","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008235303","display_name":"S. Pavankumar Dubagunta","orcid":"https://orcid.org/0000-0002-4307-8604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Pavankumar Dubagunta","raw_affiliation_strings":["Uniphore Software Systems,India","Uniphore Software Systems, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uniphore Software Systems,India","institution_ids":[]},{"raw_affiliation_string":"Uniphore Software Systems, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute,Martigny,Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute,Martigny,Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0564,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76474926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9977999925613403,"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":0.7922934293746948},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7318249344825745},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.705865204334259},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6113629341125488},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6007424592971802},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5922778844833374},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5895363688468933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098904371261597},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47505638003349304},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4598980247974396},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42986804246902466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33436527848243713}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922934293746948},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7318249344825745},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.705865204334259},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6113629341125488},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6007424592971802},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5922778844833374},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5895363688468933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098904371261597},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47505638003349304},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4598980247974396},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42986804246902466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33436527848243713},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095892","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308239","display_name":"EMI","ror":"https://ror.org/01qstkr73"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W309418507","https://openalex.org/W2061068689","https://openalex.org/W2074788634","https://openalex.org/W2088817501","https://openalex.org/W2111926505","https://openalex.org/W2123045220","https://openalex.org/W2144005487","https://openalex.org/W2146334809","https://openalex.org/W2184421965","https://openalex.org/W2239141610","https://openalex.org/W2343758848","https://openalex.org/W2400604769","https://openalex.org/W2512449761","https://openalex.org/W2515667479","https://openalex.org/W2518110751","https://openalex.org/W2533262878","https://openalex.org/W2566781703","https://openalex.org/W2770454110","https://openalex.org/W2803098682","https://openalex.org/W2887376701","https://openalex.org/W2887949187","https://openalex.org/W2889717020","https://openalex.org/W2936451900","https://openalex.org/W2936879941","https://openalex.org/W2937154351","https://openalex.org/W2962736520","https://openalex.org/W2972717745","https://openalex.org/W2997399314","https://openalex.org/W3025642987","https://openalex.org/W3036601975","https://openalex.org/W3156762052","https://openalex.org/W3163091219","https://openalex.org/W3196515791","https://openalex.org/W3207255821","https://openalex.org/W4293571337","https://openalex.org/W4297510535","https://openalex.org/W4304092044","https://openalex.org/W6677995690","https://openalex.org/W6704722722","https://openalex.org/W6713639923","https://openalex.org/W6753678270","https://openalex.org/W6761559202","https://openalex.org/W6780218876","https://openalex.org/W6794538540"],"related_works":["https://openalex.org/W2010378435","https://openalex.org/W2811390910","https://openalex.org/W2146076056","https://openalex.org/W2144059113","https://openalex.org/W3003836766","https://openalex.org/W4377970696","https://openalex.org/W1964120219","https://openalex.org/W2798765714","https://openalex.org/W2000165426","https://openalex.org/W2546942002"],"abstract_inverted_index":{"Conventionally,":[0],"speech":[1,47,77],"emotion":[2,48,78],"recognition":[3],"has":[4,37],"been":[5,38],"approached":[6],"by":[7,24],"utterance":[8],"or":[9,23],"turn-level":[10],"modelling":[11,46,76,97],"of":[12,115,134],"input":[13],"signals,":[14],"either":[15],"through":[16,111],"extracting":[17],"hand-crafted":[18,67,104],"low-level":[19],"descriptors,":[20],"bag-of-audio-words":[21],"features":[22,105],"feeding":[25],"long-duration":[26],"signals":[27],"directly":[28],"to":[29,129],"deep":[30],"neural":[31,118],"networks":[32],"(DNNs).":[33],"While":[34],"this":[35],"approach":[36,98,127],"successful,":[39],"there":[40],"is":[41,99],"a":[42],"growing":[43],"interest":[44],"in":[45,80],"information":[49,79,132,136],"at":[50,55],"the":[51,59,93,116,123],"short":[52,82],"segment":[53],"level,":[54],"around":[56],"250ms-500ms":[57],"(e.g.":[58],"2021-22":[60],"MuSe":[61],"Challenges).":[62],"This":[63],"paper":[64],"investigates":[65],"both":[66],"feature-based":[68],"and":[69,140],"end-to-end":[70,94,126],"raw":[71,95],"waveform":[72,96],"DNN":[73],"approaches":[74],"for":[75,106],"such":[81],"segments.":[83],"Through":[84],"experimental":[85],"studies":[86],"on":[87],"IEMOCAP":[88],"corpus,":[89],"we":[90,120],"demonstrate":[91],"that":[92,122],"more":[100],"effective":[101],"than":[102],"using":[103],"short-segment":[107],"level":[108],"modelling.":[109],"Furthermore,":[110],"relevance":[112],"signal-based":[113],"analysis":[114],"trained":[117],"networks,":[119],"observe":[121],"top":[124],"performing":[125],"tends":[128],"emphasize":[130],"cepstral":[131],"instead":[133],"spectral":[135],"(such":[137],"as":[138],"flux":[139],"harmonicity).":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}