{"id":"https://openalex.org/W2584374935","doi":"https://doi.org/10.1109/icassp.2017.7952705","title":"Fast tagging of natural sounds using marginal co-regularization","display_name":"Fast tagging of natural sounds using marginal co-regularization","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2584374935","doi":"https://doi.org/10.1109/icassp.2017.7952705","mag":"2584374935"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5013817745","display_name":"Qiang Huang","orcid":"https://orcid.org/0000-0003-1120-4685"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qiang Huang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022165330","display_name":"Philip J. B. Jackson","orcid":"https://orcid.org/0000-0001-7933-5935"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip J. B. Jackson","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5013817745"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00667439,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"2991","last_page":"2995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9959999918937683,"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/classifier","display_name":"Classifier (UML)","score":0.7916293740272522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7845367789268494},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6631463766098022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5260717272758484},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5181180834770203},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.449270635843277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4171414077281952},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32674917578697205}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7916293740272522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7845367789268494},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6631463766098022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5260717272758484},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5181180834770203},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.449270635843277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4171414077281952},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32674917578697205}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2017.7952705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952705","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11139477120002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:813129","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/813129/1/QH11.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W44499633","https://openalex.org/W170967611","https://openalex.org/W325132576","https://openalex.org/W1757247158","https://openalex.org/W1968154520","https://openalex.org/W1968555645","https://openalex.org/W1970578576","https://openalex.org/W1983988843","https://openalex.org/W1986765635","https://openalex.org/W2046665279","https://openalex.org/W2047779269","https://openalex.org/W2056507581","https://openalex.org/W2077945429","https://openalex.org/W2096270777","https://openalex.org/W2096873754","https://openalex.org/W2107789863","https://openalex.org/W2116373735","https://openalex.org/W2118597426","https://openalex.org/W2140676093","https://openalex.org/W2151691375","https://openalex.org/W2158542502","https://openalex.org/W2159277110","https://openalex.org/W2168441989","https://openalex.org/W2236279451","https://openalex.org/W6601738571","https://openalex.org/W6606917465","https://openalex.org/W6611110775","https://openalex.org/W6674764686","https://openalex.org/W6676071220"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4254199101","https://openalex.org/W4300427796","https://openalex.org/W4224009465","https://openalex.org/W1670153145","https://openalex.org/W4306674287","https://openalex.org/W4286629047","https://openalex.org/W2051864124","https://openalex.org/W3023929447","https://openalex.org/W2021131614"],"abstract_inverted_index":{"Automatic":[0],"and":[1,28,52,89,128,146],"fast":[2],"tagging":[3],"of":[4,23,48,107,130],"natural":[5],"sounds":[6],"in":[7,85,143],"audio":[8,59],"collections":[9],"is":[10,101],"a":[11,41,46,62,116],"very":[12],"challenging":[13],"task":[14],"due":[15],"to":[16,44,61,73,90],"wide":[17],"acoustic":[18,83],"variations,":[19],"the":[20,26,74,86,92,99,110,140],"large":[21],"number":[22],"possible":[24],"tags,":[25,76],"incomplete":[27],"ambiguous":[29],"tags":[30,72,93],"provided":[31],"by":[32,81,115],"different":[33],"labellers.":[34],"To":[35],"handle":[36],"these":[37],"problems,":[38],"we":[39],"use":[40],"co-regularization":[42,138],"approach":[43,122],"learn":[45],"pair":[47,106],"classifiers":[49,100,112],"on":[50,123],"sound":[51,125],"text.":[53],"The":[54,66,132],"first":[55,87],"classifier":[56,68],"maps":[57,69],"low-level":[58,82],"features":[60],"true":[63,75],"tag":[64],"list.":[65],"second":[67],"actively":[70],"corrupted":[71],"reducing":[77],"incorrect":[78],"mappings":[79],"caused":[80],"variations":[84],"classifier,":[88],"augment":[91],"with":[94],"additional":[95],"relevant":[96],"tags.":[97],"Training":[98],"implemented":[102],"using":[103],"marginal":[104,137],"co-regularization,":[105],"which":[108],"draws":[109],"two":[111,124],"into":[113],"agreement":[114],"joint":[117],"optimization.":[118],"We":[119],"evaluate":[120],"this":[121],"datasets,":[126],"Freefield1010":[127],"Task4":[129],"DCASE2016.":[131],"results":[133],"obtained":[134],"show":[135],"that":[136],"outperforms":[139],"baseline":[141],"GMM":[142],"both":[144],"efficiency":[145],"effectiveness.":[147]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}