{"id":"https://openalex.org/W1489641191","doi":"https://doi.org/10.1109/icassp.2011.5947690","title":"Audiovisual classification of vocal outbursts in human conversation using Long-Short-Term Memory networks","display_name":"Audiovisual classification of vocal outbursts in human conversation using Long-Short-Term Memory networks","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W1489641191","doi":"https://doi.org/10.1109/icassp.2011.5947690","mag":"1489641191"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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://eprints.nottingham.ac.uk/31428/","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":false,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, 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, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College 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 of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Human-Machine Communication, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103337935","display_name":"George Tzimiropoulos","orcid":null},"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":"George Tzimiropoulos","raw_affiliation_strings":["Department of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080553022","display_name":"Stefanos Zafeiriou","orcid":"https://orcid.org/0000-0002-5222-1740"},"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":"Stefanos Zafeiriou","raw_affiliation_strings":["Department of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"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/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]},{"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"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Department of Computing, Imperial College London, UK","EEMCS, University of Twente, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"EEMCS, University of Twente, Netherlands","institution_ids":["https://openalex.org/I94624287"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.433,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92770614,"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":"5844","last_page":"5847"},"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":0.9997000098228455,"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":0.9955999851226807,"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":0.8863187432289124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7926411032676697},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7422354817390442},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6553618907928467},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6220347285270691},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5636082887649536},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.551663339138031},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5376895666122437},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4927723705768585},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4519006609916687},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.44187596440315247},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.416027694940567},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35819607973098755},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3481498062610626},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32066255807876587},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08597919344902039}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8863187432289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7926411032676697},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7422354817390442},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6553618907928467},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6220347285270691},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5636082887649536},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.551663339138031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5376895666122437},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4927723705768585},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4519006609916687},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.44187596440315247},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.416027694940567},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35819607973098755},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3481498062610626},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32066255807876587},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08597919344902039},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/icassp.2011.5947690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ris.utwente.nl:openaire_cris_publications/56938ff6-476f-43ac-abc3-92634d39b1b7","is_oa":false,"landing_page_url":"https://research.utwente.nl/en/publications/56938ff6-476f-43ac-abc3-92634d39b1b7","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, Tzimiropoulos, G, Zafeiriou, S & Pantic, M 2011, Audiovisual classification of vocal outbursts in human conversation using long-short-term memory networks. in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011). IEEE, USA, pp. 5844-5847, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2011, Prague, Czech Republic, 22/05/11. https://doi.org/10.1109/ICASSP.2011.5947690","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.364.5197","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.364.5197","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/11/11eyb2.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.nottingham.ac.uk:31428","is_oa":true,"landing_page_url":"http://eprints.nottingham.ac.uk/31428/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402013","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1107248","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1107248","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:nottingham-repository.worktribe.com:1010611","is_oa":true,"landing_page_url":"https://nottingham-repository.worktribe.com/output/1010611","pdf_url":null,"source":{"id":"https://openalex.org/S4306402483","display_name":"Repository@Nottingham (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Presentation / Conference Contribution"},{"id":"pmh:oai:ris.utwente.nl:publications/56938ff6-476f-43ac-abc3-92634d39b1b7","is_oa":false,"landing_page_url":"http://eprints.eemcs.utwente.nl/secure2/21353/01/pantic_audivisual_classification_of_vocal_outbursts.pdf","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:71508","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-715082","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:eprints.nottingham.ac.uk:31428","is_oa":true,"landing_page_url":"http://eprints.nottingham.ac.uk/31428/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402013","display_name":"Nottingham ePrints (University of Nottingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142263535","host_organization_name":"University of Nottingham","host_organization_lineage":["https://openalex.org/I142263535"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W147964346","https://openalex.org/W150009287","https://openalex.org/W1503417225","https://openalex.org/W1969761120","https://openalex.org/W2012658661","https://openalex.org/W2032382719","https://openalex.org/W2074596973","https://openalex.org/W2077606547","https://openalex.org/W2085662862","https://openalex.org/W2102993181","https://openalex.org/W2106556719","https://openalex.org/W2134325309","https://openalex.org/W2134473538","https://openalex.org/W2144499799","https://openalex.org/W2153143911","https://openalex.org/W2155799207","https://openalex.org/W2161949887","https://openalex.org/W2163802190","https://openalex.org/W2167221531","https://openalex.org/W2170960656","https://openalex.org/W2479414554","https://openalex.org/W4235534324","https://openalex.org/W4285719527","https://openalex.org/W6679994915","https://openalex.org/W6681794868","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W4385280324","https://openalex.org/W2890685186","https://openalex.org/W2984436043","https://openalex.org/W4390245176","https://openalex.org/W2912831041","https://openalex.org/W3173606726"],"abstract_inverted_index":{"We":[0],"investigate":[1],"classification":[2],"of":[3,27,37,67],"non-linguistic":[4],"vocalisations":[5],"with":[6,58],"a":[7,71,84],"novel":[8],"audiovisual":[9],"approach":[10,73],"and":[11,47,92],"Long":[12],"Short-Term":[13],"Memory":[14],"(LSTM)":[15],"Recurrent":[16],"Neural":[17],"Networks":[18],"as":[19],"highly":[20],"successful":[21],"dynamic":[22],"sequence":[23],"classifiers.":[24],"As":[25],"database":[26],"evaluation":[28],"serves":[29],"this":[30],"year's":[31],"Paralinguistic":[32],"Challenge's":[33],"Audiovisual":[34],"Interest":[35],"Corpus":[36],"human-to-human":[38],"natural":[39],"conversation.":[40],"For":[41],"video-based":[42],"analysis":[43],"we":[44,81],"compare":[45],"shape":[46,94],"appearance":[48],"based":[49,74],"features.":[50,95],"These":[51],"are":[52],"fused":[53],"in":[54,87],"an":[55],"early":[56],"manner":[57],"typical":[59],"audio":[60,91],"descriptors.":[61],"The":[62],"results":[63],"show":[64,83],"significant":[65,85],"improvements":[66],"LSTM":[68],"networks":[69],"over":[70],"static":[72],"on":[75],"Support":[76],"Vector":[77],"Machines.":[78],"More":[79],"important,":[80],"can":[82],"gain":[86],"performance":[88],"when":[89],"fusing":[90],"visual":[93]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
