{"id":"https://openalex.org/W165447341","doi":"https://doi.org/10.21437/interspeech.2009-483","title":"On the relevance of high-level features for speaker independent emotion recognition of spontaneous speech","display_name":"On the relevance of high-level features for speaker independent emotion recognition of spontaneous speech","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W165447341","doi":"https://doi.org/10.21437/interspeech.2009-483","mag":"165447341"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5054201968","display_name":"Marko Lugger","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marko Lugger","raw_affiliation_strings":["University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101717969","display_name":"Bin Yang","orcid":"https://orcid.org/0000-0003-3322-867X"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bin Yang","raw_affiliation_strings":["University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054201968"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":1.4099,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79380327,"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":"1995","last_page":"1998"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.998199999332428,"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":0.9968000054359436,"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":0.7747042775154114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6647953987121582},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6433863639831543},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.5927591323852539},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5801411271095276},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5551653504371643},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.501997709274292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4695093333721161},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.450234055519104},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4165583550930023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.405665785074234},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10148024559020996}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7747042775154114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6647953987121582},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6433863639831543},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.5927591323852539},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5801411271095276},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5551653504371643},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.501997709274292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4695093333721161},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.450234055519104},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4165583550930023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.405665785074234},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10148024559020996},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-483","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W2064758410","https://openalex.org/W2078833921","https://openalex.org/W2083660934","https://openalex.org/W2104862701","https://openalex.org/W2152593171","https://openalex.org/W2161281622","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1987047733","https://openalex.org/W2989774764","https://openalex.org/W1914697324","https://openalex.org/W2167212246","https://openalex.org/W3006475563","https://openalex.org/W3015707499","https://openalex.org/W2049462786","https://openalex.org/W4287868249","https://openalex.org/W2326728821","https://openalex.org/W4297798768"],"abstract_inverted_index":{"In":[0],"this":[1,49],"paper":[2],"we":[3,22,30,95],"study":[4,96],"the":[5,14,55,80,87,97,104,109,121],"relevance":[6],"of":[7,16,27,43,57,86,90],"so":[8],"called":[9,59,72],"high-level":[10,37,44,106,117,134],"speech":[11],"features":[12,38,45,76,107],"for":[13,32,54,126],"application":[15],"speaker":[17,122],"independent":[18,123],"emotion":[19,132],"recognition.":[20],"After":[21],"give":[23,77],"a":[24,51,64,91],"brief":[25],"definition":[26],"highlevel":[28],"features,":[29,135,137],"discuss":[31],"which":[33],"standard":[34,110],"feature":[35,52,66,118],"groups":[36,42],"are":[39,46],"conceivable.":[40],"Two":[41],"proposed":[47,105],"within":[48],"paper:":[50],"set":[53,67],"parametrization":[56],"phonation":[58],"voice":[60,138],"quality":[61,139],"parameters":[62,140],"and":[63,83],"second":[65],"deduced":[68],"from":[69],"music":[70],"theory":[71],"harmony":[73,136],"features.":[74,112],"Harmony":[75],"information":[78],"about":[79],"frequency":[81],"interval":[82],"chord":[84],"content":[85],"pitch":[88],"data":[89],"spoken":[92],"utterance.":[93],"Finally,":[94],"gain":[98],"in":[99],"classification":[100,124],"rate":[101],"by":[102],"combining":[103],"with":[108],"low-level":[111],"We":[113],"show":[114],"that":[115],"both":[116],"sets":[119],"improve":[120],"performance":[125],"spontaneous":[127],"emotional":[128],"speech.":[129],"Index":[130],"Terms:":[131],"recognition,":[133]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}