{"id":"https://openalex.org/W2106225333","doi":"https://doi.org/10.1109/icme.2008.4607689","title":"Combining speech recognition and acoustic word emotion models for robust text-independent emotion recognition","display_name":"Combining speech recognition and acoustic word emotion models for robust text-independent emotion recognition","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2106225333","doi":"https://doi.org/10.1109/icme.2008.4607689","mag":"2106225333"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2008.4607689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2008.4607689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/77150/77150.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munchen, Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munchen, Munich","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087200921","display_name":"Bogdan Vlasenko","orcid":null},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bogdan Vlasenko","raw_affiliation_strings":["Cognitive Systems IESK, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","Cognitive Systems, IESK, Otto von Guericke University, Magdeburg, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems IESK, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]},{"raw_affiliation_string":"Cognitive Systems, IESK, Otto von Guericke University, Magdeburg, Germany#TAB#","institution_ids":["https://openalex.org/I95793202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088855123","display_name":"Dejan Arsi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dejan Arsic","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":["Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","Institute for Human-Machine Communication Technische Universitat Munchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institute for Human-Machine Communication Technische Universitat Munchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047373591","display_name":"Andreas Wendemuth","orcid":"https://orcid.org/0000-0001-6917-8198"},"institutions":[{"id":"https://openalex.org/I95793202","display_name":"Otto-von-Guericke-Universit\u00e4t Magdeburg","ror":"https://ror.org/00ggpsq73","country_code":"DE","type":"education","lineage":["https://openalex.org/I95793202"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Wendemuth","raw_affiliation_strings":["Cognitive Systems IESK, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","Cognitive Systems, IESK, Otto von Guericke University, Magdeburg, Germany#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Systems IESK, Otto-von-Guericke University of Magdeburg, Magdeburg, Germany","institution_ids":["https://openalex.org/I95793202"]},{"raw_affiliation_string":"Cognitive Systems, IESK, Otto von Guericke University, Magdeburg, Germany#TAB#","institution_ids":["https://openalex.org/I95793202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6559,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.95869738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1333","last_page":"1336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/speech-recognition","display_name":"Speech recognition","score":0.7719771265983582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686033248901367},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5875445008277893},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5245592594146729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.506217896938324},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.48375988006591797},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47663888335227966},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.463351309299469},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4497610330581665},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.41169652342796326},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2966836988925934},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10915446281433105},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07657843828201294}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7719771265983582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686033248901367},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5875445008277893},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5245592594146729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506217896938324},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.48375988006591797},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47663888335227966},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.463351309299469},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4497610330581665},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.41169652342796326},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2966836988925934},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10915446281433105},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07657843828201294},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icme.2008.4607689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2008.4607689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:77150","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-771507","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/77150/77150.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4114","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4114","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mmk.ei.tum.de/publ/pdf/08/08sch9.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:77150","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-771507","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/77150/77150.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316913","display_name":"Center for Behavioral Brain Sciences","ror":"https://ror.org/03d1zwe41"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2106225333.pdf","grobid_xml":"https://content.openalex.org/works/W2106225333.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W27187656","https://openalex.org/W71317400","https://openalex.org/W170282027","https://openalex.org/W175750906","https://openalex.org/W1973378890","https://openalex.org/W2074179263","https://openalex.org/W2110052520","https://openalex.org/W2149345536","https://openalex.org/W2747342956","https://openalex.org/W4213060595","https://openalex.org/W4239447739","https://openalex.org/W6606892395","https://openalex.org/W6682119568","https://openalex.org/W6950338138"],"related_works":["https://openalex.org/W3125750421","https://openalex.org/W2090763504","https://openalex.org/W148178222","https://openalex.org/W2104657898","https://openalex.org/W1948992892","https://openalex.org/W1886884218","https://openalex.org/W1910826599","https://openalex.org/W2012353789","https://openalex.org/W4388820305","https://openalex.org/W4221161909"],"abstract_inverted_index":{"Recognition":[0],"of":[1,23,74,94,113],"emotion":[2,19,46,115],"in":[3,125],"speech":[4],"usually":[5],"uses":[6],"acoustic":[7,45],"models":[8,55,116,121],"that":[9],"ignore":[10],"the":[11,24,42,58,92,105,126],"spoken":[12,59],"content.":[13],"Likewise":[14],"one":[15],"general":[16,120],"model":[17],"per":[18],"is":[20],"trained":[21],"independent":[22],"phonetic":[25,51],"structure.":[26],"Given":[27],"sufficient":[28,123],"data,":[29],"this":[30,37],"approach":[31],"seemingly":[32],"works":[33],"well":[34],"enough.":[35],"Yet,":[36],"paper":[38],"tries":[39],"to":[40,63,98],"answer":[41],"question":[43],"whether":[44],"recognition":[47],"strongly":[48],"depends":[49],"on":[50,104],"content,":[52],"and":[53,70,79,84],"if":[54],"tailored":[56],"for":[57],"unit":[60],"can":[61],"lead":[62],"higher":[64],"accuracies.":[65],"We":[66],"therefore":[67],"investigate":[68],"phoneme-,":[69],"word-models":[71],"by":[72],"use":[73],"a":[75],"large":[76],"prosodic,":[77],"spectral,":[78],"voice":[80],"quality":[81],"feature":[82],"space":[83],"Support":[85],"Vector":[86],"Machines":[87],"(SVM).":[88],"Experiments":[89],"also":[90],"take":[91],"necessity":[93],"ASR":[95],"into":[96],"account":[97],"select":[99],"appropriate":[100],"unit-":[101],"models.":[102],"Test-runs":[103],"well-known":[106],"EMO-DB":[107],"database":[108],"facing":[109],"speaker-independence":[110],"demonstrate":[111],"superiority":[112],"word":[114],"over":[117],"today's":[118],"common":[119],"provided":[122],"occurrences":[124],"training":[127],"corpus.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
