{"id":"https://openalex.org/W2518110751","doi":"https://doi.org/10.21437/interspeech.2016-1124","title":"At the Border of Acoustics and Linguistics: Bag-of-Audio-Words for the Recognition of Emotions in Speech","display_name":"At the Border of Acoustics and Linguistics: Bag-of-Audio-Words for the Recognition of Emotions in Speech","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2518110751","doi":"https://doi.org/10.21437/interspeech.2016-1124","mag":"2518110751"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-1124","doi":"https://doi.org/10.21437/interspeech.2016-1124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1124","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72022/schmitt16_interspeech.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019825395","display_name":"Maximilian Schmitt","orcid":"https://orcid.org/0000-0001-7453-5612","observed_orcids":["https://orcid.org/0000-0001-7453-5612"]},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maximilian Schmitt","raw_affiliation_strings":["Chair of Complex & Intelligent Systems, University of Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Complex & Intelligent Systems, University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026933067","display_name":"Fabien Ringeval","orcid":"https://orcid.org/0000-0002-9213-4529","observed_orcids":["https://orcid.org/0000-0002-9213-4529"]},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabien Ringeval","raw_affiliation_strings":["Chair of Complex & Intelligent Systems, University of Passau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Complex & Intelligent Systems, University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn Wolfgang Schuller","orcid":"https://orcid.org/0000-0002-6478-8699","observed_orcids":["https://orcid.org/0000-0002-6478-8699"]},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]},{"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":["DE","GB"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Schuller","raw_affiliation_strings":["Chair of Complex & Intelligent Systems, University of Passau, Germany","Department of Computing, Imperial College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Complex & Intelligent Systems, University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]},{"raw_affiliation_string":"Department of Computing, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.2147,"has_fulltext":true,"cited_by_count":135,"citation_normalized_percentile":{"value":0.9964485,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9937000274658203,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.0031999999191612005,"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":0.001500000013038516,"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/emotion-recognition-in-speech","display_name":"emotion recognition in speech","score":0.925000011920929},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.9509999752044678},{"id":"https://openalex.org/keywords/support-vector-regression","display_name":"support vector regression","score":0.8130000233650208},{"id":"https://openalex.org/keywords/spontaneous-emotions","display_name":"spontaneous emotions","score":0.5699999928474426},{"id":"https://openalex.org/keywords/sound-event-classification","display_name":"sound event classification","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6174801588058472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5360375642776489},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5208454728126526},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3591457009315491},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2016-1124","doi":"https://doi.org/10.21437/interspeech.2016-1124","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-1124","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72022","doi":null,"is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72022","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72022/schmitt16_interspeech.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,"listed_in":[],"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:uni-augsburg.opus-bayern.de:72022","doi":null,"is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/72022","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/72022/schmitt16_interspeech.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,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.49000000953674316,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2518110751.pdf","grobid_xml":"https://content.openalex.org/works/W2518110751.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W144301116","https://openalex.org/W1501669607","https://openalex.org/W1515999713","https://openalex.org/W1559922967","https://openalex.org/W1597064524","https://openalex.org/W1964442016","https://openalex.org/W1994458317","https://openalex.org/W2004062573","https://openalex.org/W2005418748","https://openalex.org/W2009112943","https://openalex.org/W2021913835","https://openalex.org/W2037441721","https://openalex.org/W2040232951","https://openalex.org/W2045528981","https://openalex.org/W2073459066","https://openalex.org/W2090777335","https://openalex.org/W2118585731","https://openalex.org/W2125052510","https://openalex.org/W2171939880","https://openalex.org/W2183154044","https://openalex.org/W2285774199","https://openalex.org/W2399733683","https://openalex.org/W2400604769","https://openalex.org/W2406311945","https://openalex.org/W2408491073","https://openalex.org/W4301204483"],"related_works":["https://openalex.org/W3130084382","https://openalex.org/W2888966432","https://openalex.org/W4290851120","https://openalex.org/W3035310413","https://openalex.org/W2956699086","https://openalex.org/W1534131679","https://openalex.org/W2913960490","https://openalex.org/W2765860599","https://openalex.org/W7005887284","https://openalex.org/W2183154044"],"abstract_inverted_index":{"Recognition":[0],"of":[1,31,43,56,66,71,97,129,153,169],"natural":[2,147],"emotion":[3,87,109],"in":[4,40,86,111,117],"speech":[5],"is":[6,75,104],"a":[7,63,69,91],"challenging":[8],"task.Different":[9],"methods":[10],"have":[11,36,81],"been":[12,37,83],"proposed":[13],"to":[14,62,107],"tackle":[15],"this":[16,52,124],"complex":[17],"task,":[18],"such":[19,115],"as":[20,116],"acoustic":[21,32,44,57],"feature":[22,54],"brute-forcing":[23],"or":[24],"even":[25],"endto-end":[26],"learning.Recently,":[27],"bag-of-audio-words":[28],"(BoAW)":[29],"representations":[30],"low-level":[33],"descriptors":[34],"(LLDs)":[35],"employed":[38],"successfully":[39],"the":[41,72,118,127,133,140],"domain":[42],"event":[45],"classification":[46],"and":[47,113,121,135,146,177],"other":[48],"audio":[49,67],"recognition":[50],"tasks.In":[51],"approach,":[53],"vectors":[55],"LLDs":[58],"are":[59],"quantised":[60],"according":[61],"learnt":[64],"codebook":[65],"words.Then,":[68],"histogram":[70],"occurring":[73],"'words'":[74],"built.Despite":[76],"their":[77],"massive":[78],"potential,":[79],"BoAW":[80,94,151],"not":[82,156],"thoroughly":[84],"studied":[85],"recognition.Here,":[88],"we":[89],"propose":[90],"method":[92],"using":[93],"created":[95],"only":[96,157],"mel-frequency":[98],"cepstral":[99],"coefficients":[100],"(MFCCs).Support":[101],"vector":[102],"regression":[103],"then":[105],"used":[106],"predict":[108],"continuously":[110],"time":[112],"value,":[114],"dimensions":[119],"arousal":[120],"valence.We":[122],"compare":[123],"approach":[125],"with":[126],"computation":[128],"functionals":[130],"based":[131],"on":[132,139],"MFCCs":[134,154],"perform":[136,158],"extensive":[137],"evaluations":[138],"RECOLA":[141],"database,":[142],"which":[143],"features":[144],"spontaneous":[145],"emotions.Results":[148],"show":[149],"that,":[150],"representation":[152],"does":[155],"significantly":[159],"better":[160],"than":[161],"functionals,":[162],"but":[163],"also":[164],"outperforms":[165],"by":[166],"far":[167],"most":[168],"recently":[170],"published":[171],"deep":[172],"learning":[173],"approaches,":[174],"including":[175],"convolutional":[176],"recurrent":[178],"networks.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":22},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-09-16T00:00:00"}