{"id":"https://openalex.org/W2435104358","doi":"https://doi.org/10.1109/icme.2016.7552989","title":"Weakly supervised scalable audio content analysis","display_name":"Weakly supervised scalable audio content analysis","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2435104358","doi":"https://doi.org/10.1109/icme.2016.7552989","mag":"2435104358"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2016.7552989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.03664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113017615","display_name":"Bhiksha Raj","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhiksha Raj","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080751032"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04640567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8324015736579895},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6764414310455322},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6693597435951233},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5692487359046936},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5183754563331604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5135007500648499},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5034093260765076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47992759943008423},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.44386759400367737},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3445814847946167},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08453556895256042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.06729310750961304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324015736579895},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6764414310455322},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6693597435951233},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5692487359046936},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5183754563331604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5135007500648499},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5034093260765076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47992759943008423},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.44386759400367737},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3445814847946167},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08453556895256042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.06729310750961304},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icme.2016.7552989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1606.03664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.03664","pdf_url":"https://arxiv.org/pdf/1606.03664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2435104358","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1606.03664.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1606.03664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1606.03664","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.03664","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.03664","pdf_url":"https://arxiv.org/pdf/1606.03664","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2435104358.pdf","grobid_xml":"https://content.openalex.org/works/W2435104358.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W80364729","https://openalex.org/W1650531274","https://openalex.org/W1966385142","https://openalex.org/W2010792435","https://openalex.org/W2036931953","https://openalex.org/W2048827870","https://openalex.org/W2050243593","https://openalex.org/W2066941820","https://openalex.org/W2069943693","https://openalex.org/W2088558690","https://openalex.org/W2092216166","https://openalex.org/W2100969003","https://openalex.org/W2108745803","https://openalex.org/W2110119381","https://openalex.org/W2115447976","https://openalex.org/W2121750345","https://openalex.org/W2127448212","https://openalex.org/W2129634963","https://openalex.org/W2135131618","https://openalex.org/W2137343183","https://openalex.org/W2142236629","https://openalex.org/W2147147599","https://openalex.org/W2279749074","https://openalex.org/W2408491073","https://openalex.org/W6676245398","https://openalex.org/W6677656871","https://openalex.org/W6679409316","https://openalex.org/W6712469065","https://openalex.org/W6997266731"],"related_works":["https://openalex.org/W2963547958","https://openalex.org/W2997685131","https://openalex.org/W1882520841","https://openalex.org/W2151177265","https://openalex.org/W1554745153","https://openalex.org/W2125052510","https://openalex.org/W2963828546","https://openalex.org/W2077456266","https://openalex.org/W2365160525","https://openalex.org/W2776528780","https://openalex.org/W2147570199","https://openalex.org/W1587468281","https://openalex.org/W2038338469","https://openalex.org/W2742703707","https://openalex.org/W2556103926","https://openalex.org/W2775447703","https://openalex.org/W2856235617","https://openalex.org/W2908965201","https://openalex.org/W2795332105","https://openalex.org/W2785892019"],"abstract_inverted_index":{"Audio":[0],"Event":[1],"Detection":[2],"is":[3,23,72],"an":[4],"important":[5],"task":[6],"for":[7,95],"content":[8],"analysis":[9],"of":[10,14,20,40,44],"multimedia":[11,46],"data.":[12],"Most":[13],"the":[15,41],"current":[16],"works":[17],"on":[18],"detection":[19,68,98],"audio":[21,66,96],"events":[22],"driven":[24],"through":[25,69],"supervised":[26,33],"learning":[27,34,61,82,93],"approaches.":[28],"We":[29,74],"propose":[30,76],"a":[31,77],"weakly":[32],"framework":[35],"which":[36],"can":[37],"make":[38],"use":[39,57],"tremendous":[42],"amount":[43],"web":[45],"data":[47],"with":[48,89],"significantly":[49],"reduced":[50],"annotation":[51],"effort":[52],"and":[53,84],"expense.":[54],"Specifically,":[55],"we":[56],"several":[58],"multiple":[59,80,91],"instance":[60,81,92],"algorithms":[62,94],"to":[63],"show":[64,85],"that":[65,86],"event":[67,97],"weak":[70],"labels":[71],"feasible.":[73],"also":[75],"novel":[78],"scalable":[79],"algorithm":[83],"its":[87],"competitive":[88],"other":[90],"tasks.":[99]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}