{"id":"https://openalex.org/W2131981197","doi":"https://doi.org/10.1109/tsa.2002.804546","title":"Content analysis for audio classification and segmentation","display_name":"Content analysis for audio classification and segmentation","publication_year":2002,"publication_date":"2002-10-01","ids":{"openalex":"https://openalex.org/W2131981197","doi":"https://doi.org/10.1109/tsa.2002.804546","mag":"2131981197"},"language":"en","primary_location":{"id":"doi:10.1109/tsa.2002.804546","doi":"https://doi.org/10.1109/tsa.2002.804546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsa.2002.804546","pdf_url":null,"source":{"id":"https://openalex.org/S202446260","display_name":"IEEE Transactions on Speech and Audio Processing","issn_l":"1063-6676","issn":["1063-6676","1558-2353"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Speech and Audio Processing","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2131981197"],"child_works_count":0,"type":"article","is_traditional":true,"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/A5110491600","display_name":"Lie Lu","orcid":"https://orcid.org/0009-0001-1856-8556","observed_orcids":["https://orcid.org/0009-0001-1856-8556","https://orcid.org/0009-0006-2790-7587"]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hong-Jiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Jiang Zhang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616426","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-8533-1612","observed_orcids":["https://orcid.org/0000-0002-8533-1612"]},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Simon Fraser University, Vancouver, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Simon Fraser University, Vancouver, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.5775,"has_fulltext":false,"cited_by_count":513,"citation_normalized_percentile":{"value":0.99664359,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"7","first_page":"504","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9810000061988831,"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":0.9810000061988831,"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":0.013199999928474426,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.005400000140070915,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-content-analysis","display_name":"audio content analysis","score":0.8560000061988831},{"id":"https://openalex.org/keywords/audio-classification","display_name":"audio classification","score":0.8650000095367432},{"id":"https://openalex.org/keywords/audio-segmentation","display_name":"audio segmentation","score":0.9610000252723694},{"id":"https://openalex.org/keywords/speech-non-speech-discrimination","display_name":"speech/non-speech discrimination","score":0.8550000190734863},{"id":"https://openalex.org/keywords/music-detection","display_name":"music detection","score":0.503000020980835},{"id":"https://openalex.org/keywords/silence-detection","display_name":"silence detection","score":0.9200000166893005},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"vector quantization","score":0.9509999752044678},{"id":"https://openalex.org/keywords/real-time-segmentation","display_name":"real-time segmentation","score":0.6840000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593315839767456},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6601712703704834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6533342599868774},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6315270662307739},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5787818431854248},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5542011857032776},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5493521094322205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126663446426392},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.46679314970970154},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44865745306015015},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4276415705680847},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4196265935897827},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4150991141796112},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.336654931306839},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsa.2002.804546","doi":"https://doi.org/10.1109/tsa.2002.804546","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsa.2002.804546","pdf_url":null,"source":{"id":"https://openalex.org/S202446260","display_name":"IEEE Transactions on Speech and Audio Processing","issn_l":"1063-6676","issn":["1063-6676","1558-2353"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Speech and Audio Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W139898027","https://openalex.org/W1482605500","https://openalex.org/W1545046063","https://openalex.org/W1589374915","https://openalex.org/W1607155129","https://openalex.org/W1943968395","https://openalex.org/W2023466863","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2081353817","https://openalex.org/W2095892407","https://openalex.org/W2102453655","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2109189270","https://openalex.org/W2110215948","https://openalex.org/W2111331420","https://openalex.org/W2114618792","https://openalex.org/W2124660252","https://openalex.org/W2128838222","https://openalex.org/W2129244720","https://openalex.org/W2134383396","https://openalex.org/W2146855196","https://openalex.org/W2151299225","https://openalex.org/W2160876944","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2110215948","https://openalex.org/W1505126044","https://openalex.org/W2144345993","https://openalex.org/W2083837083","https://openalex.org/W1987426045","https://openalex.org/W1575729891","https://openalex.org/W1555515114","https://openalex.org/W2079251883","https://openalex.org/W2145422964","https://openalex.org/W2041727443"],"abstract_inverted_index":{"We":[0,26,129],"present":[1],"our":[2],"study":[3],"of":[4,34,65,111],"audio":[5,15,21,39],"content":[6],"analysis":[7],"for":[8,59],"classification":[9,49,67,107],"and":[10,36,46,70,83,102,120,125,144,162],"segmentation,":[11],"in":[12,52,127],"which":[13,55],"an":[14,38,132],"stream":[16,40],"is":[17,32,50,68,89],"segmented":[18],"according":[19],"to":[20],"type":[22],"or":[23],"speaker":[24,134,160],"identity.":[25],"propose":[27],"a":[28,76,105,138,149],"robust":[29],"approach":[30],"that":[31,169],"capable":[33],"classifying":[35],"segmenting":[37],"into":[41,98],"speech,":[42],"music,":[43,99],"environment":[44,100],"sound,":[45],"silence.":[47],"Audio":[48],"processed":[51],"two":[53],"steps,":[54],"makes":[56],"it":[57],"suitable":[58],"different":[60],"applications.":[61],"The":[62,91],"first":[63],"step":[64,93],"the":[66,116,156,170],"speech":[69],"nonspeech":[71,96],"discrimination.":[72],"In":[73],"this":[74,152],"step,":[75],"novel":[77,139],"algorithm":[78,136,153],"based":[79,141],"on":[80,142],"K-nearest-neighbor":[81],"(KNN)":[82],"linear":[84],"spectral":[85],"pairs-vector":[86],"quantization":[87],"(LSP-VQ)":[88],"developed.":[90],"second":[92],"further":[94],"divides":[95],"class":[97],"sounds,":[101],"silence":[103],"with":[104],"rule-based":[106],"scheme.":[108],"A":[109],"set":[110],"new":[112],"features":[113],"such":[114],"as":[115],"noise":[117],"frame":[118],"ratio":[119],"band":[121],"periodicity":[122],"are":[123],"introduced":[124],"discussed":[126],"detail.":[128],"also":[130],"develop":[131],"unsupervised":[133],"segmentation":[135],"using":[137],"scheme":[140],"quasi-GMM":[143],"LSP":[145],"correlation":[146],"analysis.":[147],"Without":[148],"priori":[150],"knowledge,":[151],"can":[154,173],"support":[155],"open-set":[157],"speaker,":[158],"online":[159],"modeling":[161],"real":[163],"time":[164],"segmentation.":[165],"Experimental":[166],"results":[167],"indicate":[168],"proposed":[171],"algorithms":[172],"produce":[174],"very":[175],"satisfactory":[176],"results.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":28}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}