{"id":"https://openalex.org/W2152990941","doi":"https://doi.org/10.1109/icme.2003.1221025","title":"Audio classification based on maximum entropy model","display_name":"Audio classification based on maximum entropy model","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2152990941","doi":"https://doi.org/10.1109/icme.2003.1221025","mag":"2152990941"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2003.1221025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","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/A5063460883","display_name":"Zhe Feng","orcid":"https://orcid.org/0000-0001-6036-375X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Feng","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100559702","display_name":"Yaqian Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaqian Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102516427","display_name":"Lide Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lide Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011736023","display_name":"Zongge Li","orcid":"https://orcid.org/0000-0002-4860-1599"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongge Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2966,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60661765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3461","issue":null,"first_page":"I","last_page":"745"},"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":0.9959999918937683,"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":0.9891999959945679,"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":0.8158928155899048},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6509818434715271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6010535359382629},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5639861226081848},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49946117401123047},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4590105414390564},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43094584345817566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43018990755081177},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42905789613723755},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4150984287261963},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3537357747554779},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.30640989542007446},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.30575746297836304},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2956587076187134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8158928155899048},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6509818434715271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6010535359382629},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5639861226081848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49946117401123047},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4590105414390564},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43094584345817566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43018990755081177},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42905789613723755},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4150984287261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537357747554779},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.30640989542007446},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.30575746297836304},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2956587076187134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2003.1221025","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2003.1221025","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.862.7203","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.862.7203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mirlab.org/conference_papers/International_Conference/ICME%202003/pdfs/0100745.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1970704574","https://openalex.org/W2057613716","https://openalex.org/W2081353817","https://openalex.org/W2106055371","https://openalex.org/W2110215948","https://openalex.org/W2128838222","https://openalex.org/W2160842254","https://openalex.org/W2164434191","https://openalex.org/W2917578068","https://openalex.org/W6670686737"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2109142991","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W1546240199","https://openalex.org/W1911859126","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926"],"abstract_inverted_index":{"Audio":[0],"classification":[1,48],"has":[2],"been":[3],"investigated":[4],"for":[5,95],"several":[6],"years.":[7],"It":[8],"is":[9,28],"one":[10],"of":[11],"the":[12,23,33,38],"key":[13],"components":[14],"in":[15,82],"audio":[16,47],"and":[17,32,72,98],"video":[18],"applications.":[19],"In":[20,40],"prior":[21],"work,":[22],"accuracy":[24],"under":[25],"complicated":[26],"condition":[27],"not":[29],"satisfactory":[30],"enough":[31],"results":[34],"highly":[35],"depend":[36],"on":[37,51,59],"dataset.":[39],"this":[41,57,91],"paper,":[42],"we":[43],"present":[44],"a":[45,73],"novel":[46],"method":[49,58,92],"based":[50],"maximum":[52],"entropy":[53],"model.":[54],"By":[55],"applying":[56],"some":[60],"widely":[61],"used":[62],"features,":[63],"different":[64],"feature":[65,88],"combinations":[66],"are":[67],"considered":[68],"during":[69],"model":[70],"training":[71],"better":[74],"performance":[75],"can":[76],"be":[77],"achieved.":[78],"When":[79],"evaluated":[80],"it":[81],"TREC":[83],"2002":[84],"Video":[85],"Track's":[86],"speech/music":[87],"extraction":[89],"task,":[90],"works":[93],"well":[94],"both":[96],"speech":[97],"music":[99],"among":[100],"participated":[101],"systems.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}