{"id":"https://openalex.org/W2895120452","doi":"https://doi.org/10.1145/3242969.3243683","title":"Deep End-to-End Representation Learning for Food Type Recognition from Speech","display_name":"Deep End-to-End Representation Learning for Food Type Recognition from Speech","publication_year":2018,"publication_date":"2018-10-02","ids":{"openalex":"https://openalex.org/W2895120452","doi":"https://doi.org/10.1145/3242969.3243683","mag":"2895120452"},"language":"en","primary_location":{"id":"doi:10.1145/3242969.3243683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243683","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","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/44167/44167.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008305672","display_name":"Benjamin Sertolli","orcid":"https://orcid.org/0000-0002-7020-9331"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benjamin Sertolli","raw_affiliation_strings":["University of Augsburg, Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090485343","display_name":"Nicholas Cummins","orcid":"https://orcid.org/0000-0002-1178-917X"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nicholas Cummins","raw_affiliation_strings":["University of Augsburg, Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg, Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045216943","display_name":"Abdulkadir \u015eeng\u00fcr","orcid":"https://orcid.org/0000-0003-1614-2639"},"institutions":[{"id":"https://openalex.org/I143396566","display_name":"F\u0131rat University","ror":"https://ror.org/05teb7b63","country_code":"TR","type":"education","lineage":["https://openalex.org/I143396566"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Abdulkadir Sengur","raw_affiliation_strings":["Firat University, Elazig, Turkey"],"affiliations":[{"raw_affiliation_string":"Firat University, Elazig, Turkey","institution_ids":["https://openalex.org/I143396566"]}]},{"author_position":"last","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/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":"Bjoern W. Schuller","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008305672"],"corresponding_institution_ids":["https://openalex.org/I179225836"],"apc_list":null,"apc_paid":null,"fwci":0.3384,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.69267624,"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":"574","last_page":"578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9868000149726868,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9868000149726868,"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":0.9857000112533569,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9225000143051147,"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/computer-science","display_name":"Computer science","score":0.7851794958114624},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6531476378440857},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6370543837547302},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.634943962097168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6325678825378418},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5846325159072876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5513578653335571},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5293154120445251},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5089836120605469},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.48464637994766235},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4415627121925354},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4285633862018585},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41463980078697205},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12064546346664429}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7851794958114624},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6531476378440857},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6370543837547302},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.634943962097168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6325678825378418},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5846325159072876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5513578653335571},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5293154120445251},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5089836120605469},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.48464637994766235},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4415627121925354},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4285633862018585},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41463980078697205},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12064546346664429},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3242969.3243683","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3242969.3243683","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:44167","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-441677","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/44167/44167.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":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:44167","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-441677","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/44167/44167.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":"","raw_type":"bookpart"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger"}],"awards":[{"id":"https://openalex.org/G4022183372","display_name":null,"funder_award_id":"338164","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2895120452.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W331694525","https://openalex.org/W1494198834","https://openalex.org/W1994544878","https://openalex.org/W2061436640","https://openalex.org/W2064675550","https://openalex.org/W2101234009","https://openalex.org/W2107878631","https://openalex.org/W2146897752","https://openalex.org/W2168647804","https://openalex.org/W2170653751","https://openalex.org/W2296527405","https://openalex.org/W2368429174","https://openalex.org/W2399733683","https://openalex.org/W2407349954","https://openalex.org/W2407379236","https://openalex.org/W2520160253","https://openalex.org/W2554320282","https://openalex.org/W2560025328","https://openalex.org/W2578895956","https://openalex.org/W2602344811","https://openalex.org/W2605606367","https://openalex.org/W2611666824","https://openalex.org/W2615063356","https://openalex.org/W2648194195","https://openalex.org/W2744822616","https://openalex.org/W2746419079","https://openalex.org/W2747270953","https://openalex.org/W2748702193","https://openalex.org/W2750666523","https://openalex.org/W2751820872","https://openalex.org/W2754998475","https://openalex.org/W2765860599","https://openalex.org/W2766272105","https://openalex.org/W2767461737","https://openalex.org/W2781384251","https://openalex.org/W2894971724","https://openalex.org/W2949197413","https://openalex.org/W2962949934","https://openalex.org/W2963066927","https://openalex.org/W2963383024","https://openalex.org/W2997591727"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W2748667022","https://openalex.org/W3211770882","https://openalex.org/W2010629964"],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2,62,73,92,117,123],"Convolutional":[3],"Neural":[4,100],"Networks":[5],"(CNN)":[6],"pre-trained":[7,49],"for":[8,16,41,59,77,107],"a":[9,13,21,48,56,98,108],"particular":[10],"task,":[11,19],"as":[12,55],"feature":[14,57,80],"extractor":[15,58],"an":[17,113],"alternate":[18],"is":[20],"standard":[22],"practice":[23],"in":[24],"many":[25],"image":[26],"classification":[27,43,111],"paradigms.":[28],"However,":[29],"to":[30],"date":[31],"there":[32],"have":[33],"been":[34],"comparatively":[35],"few":[36],"works":[37],"exploring":[38],"this":[39,93],"technique":[40],"speech":[42],"tasks.":[44],"Herein,":[45],"we":[46,68],"utilise":[47],"end-to-end":[50],"Automatic":[51],"Speech":[52],"Recognition":[53],"CNN":[54],"the":[60,71,84,90,120,124],"task":[61,112],"food-type":[63,110],"recognition":[64],"from":[65,83],"speech.":[66],"Furthermore,":[67],"also":[69],"explore":[70],"benefits":[72],"Compact":[74],"Bilinear":[75],"Pooling":[76],"combining":[78],"multiple":[79],"representations":[81],"extracted":[82],"CNN.":[85],"Key":[86],"results":[87],"presented":[88],"indicate":[89],"suitability":[91],"approach.":[94],"When":[95],"combined":[96],"with":[97],"Recurrent":[99],"Network":[101],"classifier,":[102],"our":[103],"strongest":[104],"system":[105],"achieves,":[106],"seven-class":[109],"unweighted":[114],"average":[115],"recall":[116],"73.3%":[118],"on":[119],"test":[121],"set":[122],"iHEARu-EAT":[125],"database.":[126]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}