{"id":"https://openalex.org/W2889174280","doi":"https://doi.org/10.1109/ssp.2018.8450848","title":"Audio Classification Based on Weakly Labeled Data","display_name":"Audio Classification Based on Weakly Labeled Data","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2889174280","doi":"https://doi.org/10.1109/ssp.2018.8450848","mag":"2889174280"},"language":"en","primary_location":{"id":"doi:10.1109/ssp.2018.8450848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp.2018.8450848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Statistical Signal Processing Workshop (SSP)","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/A5112384479","display_name":"Chieh-Feng Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chieh-Feng Cheng","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033437141","display_name":"David V. Anderson","orcid":"https://orcid.org/0000-0002-8571-4613"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David V. Anderson","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064232831","display_name":"Mark A. Davenport","orcid":"https://orcid.org/0000-0001-6079-6328"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark A. Davenport","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003504268","display_name":"Abbas Rashidi","orcid":"https://orcid.org/0000-0002-4342-0588"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abbas Rashidi","raw_affiliation_strings":["University of Utah"],"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112384479"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.1651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44646291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"568","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9923999905586243,"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":0.8305010795593262},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.6768541932106018},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5876637697219849},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5460633039474487},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.520354688167572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4531734585762024},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4216074049472809},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.41131338477134705},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40761661529541016},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.24164873361587524},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1962035596370697},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10050806403160095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305010795593262},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.6768541932106018},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5876637697219849},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5460633039474487},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.520354688167572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4531734585762024},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4216074049472809},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.41131338477134705},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40761661529541016},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.24164873361587524},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1962035596370697},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10050806403160095}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssp.2018.8450848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssp.2018.8450848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Statistical Signal Processing Workshop (SSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W13034104","https://openalex.org/W1158935686","https://openalex.org/W2155998647","https://openalex.org/W2354870669","https://openalex.org/W2525577390","https://openalex.org/W2592944988","https://openalex.org/W2604490051","https://openalex.org/W2654517624","https://openalex.org/W2704368076","https://openalex.org/W2763971240","https://openalex.org/W2963099423","https://openalex.org/W3027169863","https://openalex.org/W3103314642","https://openalex.org/W3120421331","https://openalex.org/W6745117180","https://openalex.org/W6778029303"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2122358895","https://openalex.org/W2595321413","https://openalex.org/W3108971846","https://openalex.org/W2157515074"],"abstract_inverted_index":{"Audio":[0],"event":[1],"detection":[2],"and":[3,26,42,89,141,144],"classification":[4,67],"are":[5],"critical":[6],"tasks":[7],"in":[8],"the":[9,49,57,94,98,108,113,123,127,134,152],"analysis":[10],"of":[11,36,52,56,97,112,119,126],"multimedia":[12,37],"data.":[13,58,74],"Most":[14],"current":[15],"research":[16],"on":[17,21,122],"this":[18,79],"topic":[19],"focuses":[20],"processing":[22],"strongly":[23,86],"labeled":[24,73,87,110],"data":[25,38,88,114,120,143],"using":[27,137],"fully":[28],"supervised":[29],"machine":[30],"learning":[31],"techniques.":[32],"However,":[33],"many":[34],"sources":[35],"lack":[39],"detailed":[40],"annotation":[41],"rather":[43],"have":[44],"only":[45],"high-level":[46],"meta-data":[47],"describing":[48],"main":[50],"content":[51],"various":[53],"long":[54],"segments":[55],"We":[59,132],"propose":[60],"a":[61],"novel":[62],"framework":[63,136],"to":[64,78,82,91],"perform":[65],"audio":[66],"when":[68],"working":[69],"with":[70,93],"such":[71],"weakly":[72,109],"A":[75],"traditional":[76,153],"approach":[77,105],"problem":[80],"is":[81],"use":[83],"techniques":[84],"for":[85],"then":[90],"deal":[92],"weak":[95],"nature":[96],"labels":[99],"via":[100],"post-processing.":[101],"In":[102],"contrast,":[103],"our":[104,147],"directly":[106],"addresses":[107],"aspect":[111],"by":[115],"classifying":[116],"longer":[117],"windows":[118],"based":[121],"clustering":[124],"behavior":[125],"acoustic":[128],"features":[129],"over":[130],"time.":[131],"evaluate":[133],"proposed":[135],"both":[138],"synthetic":[139],"datasets":[140],"real":[142],"demonstrate":[145],"that":[146],"method":[148],"can":[149],"significantly":[150],"outperform":[151],"approach.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
