{"id":"https://openalex.org/W105569935","doi":"https://doi.org/10.21437/interspeech.2007-611","title":"Combining frame and turn-level information for robust recognition of emotions within speech","display_name":"Combining frame and turn-level information for robust recognition of emotions within speech","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W105569935","doi":"https://doi.org/10.21437/interspeech.2007-611","mag":"105569935"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-611","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76717/76717.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087200921","display_name":"Bogdan Vlasenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bogdan Vlasenko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047373591","display_name":"Andreas Wendemuth","orcid":"https://orcid.org/0000-0001-6917-8198"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Wendemuth","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5039092855","display_name":"Gerhard Rigoll","orcid":"https://orcid.org/0000-0003-1096-1596"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Rigoll","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087200921"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8364,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.9667085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7080647349357605},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6426473259925842},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5843001008033752},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.43546727299690247},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3704226613044739},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32816389203071594},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13126063346862793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080647349357605},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6426473259925842},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5843001008033752},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.43546727299690247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3704226613044739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32816389203071594},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13126063346862793}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2007-611","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76717","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/76717","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76717/76717.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":null,"raw_type":"doc-type:bookpart"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.4133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.4133","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/07/07vla1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.3107","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.3107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://iesk.et.uni-magdeburg.de/ko/papers/INTERSPEECH_2007_BV.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:76717","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/76717","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/76717/76717.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":null,"raw_type":"doc-type:bookpart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W105569935.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W170282027","https://openalex.org/W175750906","https://openalex.org/W179777611","https://openalex.org/W2050373581","https://openalex.org/W2069883713","https://openalex.org/W2074179263","https://openalex.org/W2110052520","https://openalex.org/W2149345536"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2536562190","https://openalex.org/W2389546251","https://openalex.org/W2951359407","https://openalex.org/W2124566234","https://openalex.org/W2369556382","https://openalex.org/W3136979370","https://openalex.org/W3126677997"],"abstract_inverted_index":{"Current":[0],"approaches":[1],"to":[2,98],"the":[3,37,44,112,129],"recognition":[4,87],"of":[5,17,46,48,94,131],"emotion":[6,86],"within":[7,51],"speech":[8,101],"usually":[9],"use":[10,59,91],"statistic":[11],"feature":[12,53,132],"information":[13,32,50],"obtained":[14],"by":[15,122],"application":[16],"functionals":[18,97],"on":[19,33,111,134],"turn-":[20],"or":[21],"chunk":[22],"levels.":[23],"Yet,":[24],"it":[25],"is":[26,39,120],"well":[27],"known":[28],"that":[29],"thereby":[30],"important":[31],"temporal":[34],"sub-layers":[35],"as":[36],"frame-level":[38,56],"lost.":[40],"We":[41],"therefore":[42],"investigate":[43],"benefits":[45,130],"integration":[47,133],"such":[49],"turn-level":[52,84],"space.":[54],"For":[55],"analysis":[57,119],"we":[58,90],"GMM":[60],"for":[61],"classification":[62],"and":[63,66,96,103,116],"39":[64],"MFCC":[65],"energy":[67],"features":[68],"with":[69],"CMS.":[70],"In":[71],"a":[72,81,92],"subsequent":[73],"step":[74],"output":[75],"scores":[76],"are":[77,108],"fed":[78],"forward":[79],"into":[80],"1.4k":[82],"large-feature-space":[83],"SVM":[85],"engine.":[88],"Thereby":[89],"variety":[93],"Low-Level-Descriptors":[95],"cover":[99],"prosodic,":[100],"quality,":[102],"articulatory":[104],"aspects.":[105],"Extensive":[106],"testruns":[107],"carried":[109],"out":[110],"public":[113],"databases":[114],"EMO-DB":[115],"SUSAS.":[117],"Speaker-independent":[118],"faced":[121],"speaker":[123],"normalization.":[124],"Overall":[125],"results":[126],"highly":[127],"emphasize":[128],"diverse":[135],"time":[136],"scales.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
