{"id":"https://openalex.org/W2164429204","doi":"https://doi.org/10.1109/icassp.2012.6289067","title":"Audiovisual vocal outburst classification in noisy acoustic conditions","display_name":"Audiovisual vocal outburst classification in noisy acoustic conditions","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2164429204","doi":"https://doi.org/10.1109/icassp.2012.6289067","mag":"2164429204"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1137842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","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":true,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["Institute for Human-Machine-Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine-Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","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, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Human-Machine-Communication, Technische Universit\u00e4t M\u00fcnchen, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Department of Computing, Imperial College London, London, UK","EEMCS, University of Twente, Enschede, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"EEMCS, University of Twente, Enschede, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023264395"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.737,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88309546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"5078","issue":null,"first_page":"5097","last_page":"5100"},"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/T11309","display_name":"Music 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":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/paralanguage","display_name":"Paralanguage","score":0.7970679402351379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7850334644317627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7183424234390259},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6876160502433777},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5517572164535522},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.507918655872345},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5037478804588318},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4648377597332001},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.43394210934638977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4276679456233978},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4098471403121948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32570546865463257},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07989603281021118}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7970679402351379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850334644317627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7183424234390259},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6876160502433777},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5517572164535522},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.507918655872345},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5037478804588318},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4648377597332001},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.43394210934638977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4276679456233978},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4098471403121948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32570546865463257},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07989603281021118},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2012.6289067","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/136a1f81-dfc9-422b-addc-315070b8cd94","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/136a1f81-dfc9-422b-addc-315070b8cd94","pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Eyben, F, Petridis, S, Schuller, B & Pantic, M 2012, Audiovisual vocal outburst classification in noisy conditions. in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012. IEEE, USA, pp. 5097-5100, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2012, Kyoto, Japan, 25/03/12. https://doi.org/10.1109/ICASSP.2012.6289067","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.371.4045","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.371.4045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ibug.doc.ic.ac.uk/media/uploads/documents/eybenetal_icassp2012.pdf","raw_type":"text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1137842","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:ris.utwente.nl:publications/136a1f81-dfc9-422b-addc-315070b8cd94","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922991","display_name":"University of Twente Research Information","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72635","is_oa":false,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72635","pdf_url":null,"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"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1137842","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1137842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W1489641191","https://openalex.org/W1503417225","https://openalex.org/W2032382719","https://openalex.org/W2064675550","https://openalex.org/W2085662862","https://openalex.org/W2101609565","https://openalex.org/W2102993181","https://openalex.org/W2134473538","https://openalex.org/W2138862063","https://openalex.org/W2145024093","https://openalex.org/W2151484683","https://openalex.org/W2155799207","https://openalex.org/W2167221531","https://openalex.org/W2168069730","https://openalex.org/W2170960656","https://openalex.org/W6630231184","https://openalex.org/W6682194319"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"investigate":[4],"an":[5],"audiovisual":[6],"approach":[7],"for":[8,77],"classification":[9],"of":[10,31,48,69,88,112],"vocal":[11],"outbursts":[12],"(non-linguistic":[13],"vocalisations)":[14],"in":[15,72],"noisy":[16],"conditions":[17,109],"using":[18],"Long":[19],"Short-Term":[20],"Memory":[21],"(LSTM)":[22],"Recurrent":[23],"Neural":[24],"Networks":[25],"and":[26,35,55],"Support":[27],"Vector":[28],"Machines.":[29],"Fusion":[30],"geometric":[32],"shape":[33],"features":[34,114],"acoustic":[36,49],"low-level":[37],"descriptors":[38],"is":[39,99,115],"performed":[40,100],"on":[41,61,101],"the":[42,67,70,80,107,110],"feature":[43],"level.":[44],"Three":[45],"different":[46],"types":[47],"noise":[50,63,102],"are":[51,59],"considered:":[52],"babble,":[53],"office":[54],"street":[56],"noise.":[57],"Experiments":[58],"conducted":[60],"every":[62],"type":[64],"to":[65],"asses":[66],"benefit":[68],"fusion":[71],"each":[73],"case.":[74],"As":[75],"database":[76],"evaluations":[78],"serves":[79],"INTERSPEECH":[81],"2010":[82],"Paralinguistic":[83],"Challenge's":[84],"Audiovisual":[85],"Interest":[86],"Corpus":[87],"human-to-human":[89],"natural":[90],"conversation.":[91],"The":[92],"results":[93],"show":[94],"that":[95],"even":[96],"when":[97],"training":[98],"corrupted":[103],"audio":[104],"which":[105],"matches":[106],"test":[108],"addition":[111],"visual":[113],"still":[116],"beneficial.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-03-16T09:10:04.655348","created_date":"2025-10-10T00:00:00"}
