{"id":"https://openalex.org/W2110709236","doi":"https://doi.org/10.1109/asru.2007.4430180","title":"Comparing one and two-stage acoustic modeling in the recognition of emotion in speech","display_name":"Comparing one and two-stage acoustic modeling in the recognition of emotion in speech","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2110709236","doi":"https://doi.org/10.1109/asru.2007.4430180","mag":"2110709236"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","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/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","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":"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/A5012126833","display_name":"R. Elices M\u00ednguez","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":"Ricardo Minguez","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":3.6202,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.95069532,"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":"596","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/chunking","display_name":"Chunking (psychology)","score":0.8040359616279602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7893253564834595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795118689537048},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5218093395233154},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4774375855922699},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4666234254837036},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.45802339911460876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4532928168773651},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43712860345840454},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4365866184234619},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4177360534667969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40501341223716736},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.367256760597229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3612399697303772}],"concepts":[{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.8040359616279602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7893253564834595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795118689537048},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5218093395233154},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4774375855922699},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4666234254837036},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.45802339911460876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4532928168773651},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43712860345840454},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4365866184234619},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4177360534667969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40501341223716736},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.367256760597229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3612399697303772},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2007.4430180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W71317400","https://openalex.org/W170282027","https://openalex.org/W175750906","https://openalex.org/W2074179263","https://openalex.org/W2110052520","https://openalex.org/W2149345536","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/W3184246804","https://openalex.org/W2057635330","https://openalex.org/W4319161892","https://openalex.org/W4200040515","https://openalex.org/W2542746790","https://openalex.org/W1558302546","https://openalex.org/W4214818988","https://openalex.org/W3037354152","https://openalex.org/W2168417340","https://openalex.org/W2402157757"],"abstract_inverted_index":{"In":[0,48],"the":[1,20],"search":[2,90],"for":[3,7,72,130],"a":[4,15,29,51],"standard":[5],"unit":[6],"use":[8],"in":[9,13,28],"recognition":[10],"of":[11,23,43,63],"emotion":[12],"speech,":[14],"whole":[16],"turn,":[17],"that":[18],"is":[19,31,46,54,97,101],"full":[21],"section":[22],"speech":[24],"by":[25,61,86,103],"one":[26],"person":[27],"conversation,":[30],"common.":[32],"Within":[33],"applications":[34],"such":[35],"turns":[36],"often":[37],"seem":[38],"favorable.":[39],"Yet,":[40],"high":[41],"effectiveness":[42],"sub-turn":[44],"entities":[45],"known.":[47],"this":[49],"respect":[50],"two-stage":[52],"approach":[53],"investigated":[55],"to":[56,66,123],"provide":[57],"higher":[58],"temporal":[59],"resolution":[60],"chunking":[62,79],"speech-turns":[64],"according":[65],"acoustic":[67],"properties,":[68],"and":[69,115],"multi-instance":[70],"learning":[71],"turn-mapping":[73],"after":[74],"individual":[75],"chunk":[76],"analysis.":[77],"For":[78],"fast":[80],"pre-segmentation":[81],"into":[82],"emotionally":[83],"quasi-stationary":[84],"segments":[85],"one-pass":[87],"Viterbi":[88],"beam":[89],"with":[91,109],"token":[92],"passing":[93],"basing":[94],"on":[95],"MFCC":[96],"used.":[98],"Chunk":[99],"analysis":[100],"realized":[102],"brute-force":[104],"large":[105],"feature":[106],"space":[107],"construction":[108],"subsequent":[110],"subset":[111],"selection,":[112],"SVM":[113],"classification,":[114],"speaker":[116],"normalization.":[117],"Extensive":[118],"tests":[119],"reveal":[120],"differences":[121],"compared":[122],"one-stage":[124],"processing.":[125],"Alternatively,":[126],"syllables":[127],"are":[128],"used":[129],"chunking.":[131]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}