{"id":"https://openalex.org/W2140134324","doi":"https://doi.org/10.1109/icassp.2011.5946426","title":"A hierarchical generative model for Generic Audio Document Categorization","display_name":"A hierarchical generative model for Generic Audio Document Categorization","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2140134324","doi":"https://doi.org/10.1109/icassp.2011.5946426","mag":"2140134324"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100410706","display_name":"Zhi Zeng","orcid":"https://orcid.org/0000-0003-2150-2088"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zeng","raw_affiliation_strings":["Institute of Automation, Chinese Academy and Sciences, Beijing, China","Institute of Automation Chinese Academy of Sciences  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences  Beijing China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109291841","display_name":"Shuwu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwu Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy and Sciences, Beijing, China","Institute of Automation Chinese Academy of Sciences  Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]},{"raw_affiliation_string":"Institute of Automation Chinese Academy of Sciences  Beijing China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"405","last_page":"408"},"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":0.9926999807357788,"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":0.9739000201225281,"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/discriminative-model","display_name":"Discriminative model","score":0.8332780599594116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7568171620368958},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6361317038536072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5925434231758118},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5606012940406799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5209971070289612},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4769917130470276},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45923811197280884},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4556073248386383},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44956302642822266},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4301323890686035},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4224906861782074},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.4114747941493988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3470606803894043},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2297857701778412},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11909279227256775},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08594810962677002}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8332780599594116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7568171620368958},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6361317038536072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5925434231758118},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5606012940406799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5209971070289612},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4769917130470276},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45923811197280884},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4556073248386383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44956302642822266},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4301323890686035},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4224906861782074},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4114747941493988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3470606803894043},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2297857701778412},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11909279227256775},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08594810962677002},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5946426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2100454127","https://openalex.org/W2104352833","https://openalex.org/W2106284094","https://openalex.org/W2128637751","https://openalex.org/W2133824856"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4241564561"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"call":[4],"the":[5,40,47,72,93,105,110,116,146,160],"pattern":[6],"classification":[7],"problem":[8],"that":[9],"consists":[10],"in":[11,57,69,115],"assigning":[12],"a":[13,17,53,98,151],"category":[14,76],"label":[15],"to":[16,38,71,91,103,121,150],"long":[18],"audio":[19,42,78,125,148],"signal":[20],"based":[21],"on":[22],"its":[23],"semantic":[24],"content":[25],"as":[26],"Generic":[27],"Audio":[28],"Document":[29],"Categorization":[30],"(GADC).":[31],"A":[32],"novel":[33],"generative":[34],"model":[35,51,56,94,106,118],"is":[36,52,119,129,138],"proposed":[37],"describe":[39],"generic":[41,124],"document":[43,100,126],"categories":[44],"and":[45,64,77,96],"solve":[46],"GADC":[48],"problem.":[49],"This":[50,128],"four-level":[54],"hierarchical":[55],"which":[58],"two":[59,73,87],"latent":[60],"variables":[61,75],"\"audio":[62,65,113,154],"topic\"":[63,114],"word\"":[66],"are":[67],"introduced":[68],"addition":[70],"observed":[74],"feature.":[79],"We":[80],"present":[81],"an":[82],"iterative":[83],"learning":[84],"algorithm":[85],"including":[86],"Expectation-Maximization":[88],"(EM)":[89],"cycles":[90],"estimate":[92],"parameters":[95],"give":[97],"discriminative":[99],"weighting":[101],"procedure":[102],"make":[104],"more":[107],"discriminative.":[108],"Subsequently,":[109],"distribution":[111],"of":[112,153,162],"well-trained":[117],"utilized":[120],"represent":[122],"each":[123],"category.":[127],"same":[130],"with":[131],"some":[132],"bag-of-word":[133],"methods.":[134],"However,":[135],"our":[136,163],"method":[137],"advanced":[139],"since":[140],"it":[141],"does":[142],"not":[143],"require":[144],"quantizing":[145],"continuous":[147],"features":[149],"vocabulary":[152],"words\".":[155],"Finally,":[156],"experiment":[157],"results":[158],"show":[159],"effectiveness":[161],"approach.":[164]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}