{"id":"https://openalex.org/W2004489939","doi":"https://doi.org/10.1145/1460096.1460116","title":"On enabling techniques for personal audio content management","display_name":"On enabling techniques for personal audio content management","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2004489939","doi":"https://doi.org/10.1145/1460096.1460116","mag":"2004489939"},"language":"en","primary_location":{"id":"doi:10.1145/1460096.1460116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460096.1460116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international conference on Multimedia information retrieval","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/A5087629198","display_name":"Tommi Lahti","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Tommi Lahti","raw_affiliation_strings":["Nokia Research Center, Tampere, Finland","Nokia Res. Center, Tampere, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Nokia Research Center, Tampere, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Res. Center, Tampere, Finland#TAB#","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088417423","display_name":"Marko Hel\u00e9n","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Marko Hel\u00e9n","raw_affiliation_strings":["Tampere University of Technology, Tampere, Finland","Tampere University of Technology , Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology , Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042764084","display_name":"Olli Vuorinen","orcid":null},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Olli Vuorinen","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland","VTT, Technical Research Center of Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]},{"raw_affiliation_string":"VTT, Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014100221","display_name":"Eero V\u00e4yrynen","orcid":"https://orcid.org/0000-0002-9141-3868"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eero V\u00e4yrynen","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083706088","display_name":"Juha Partala","orcid":"https://orcid.org/0000-0001-8181-5604"},"institutions":[{"id":"https://openalex.org/I98381234","display_name":"University of Oulu","ror":"https://ror.org/03yj89h83","country_code":"FI","type":"education","lineage":["https://openalex.org/I98381234"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juha Partala","raw_affiliation_strings":["University of Oulu, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"University of Oulu, Oulu, Finland","institution_ids":["https://openalex.org/I98381234"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076850081","display_name":"Johannes Peltola","orcid":"https://orcid.org/0000-0002-6248-152X"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Johannes Peltola","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland","VTT, Technical Research Center of Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]},{"raw_affiliation_string":"VTT, Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023800350","display_name":"Satu-Marja M\u00e4kel\u00e4","orcid":"https://orcid.org/0000-0003-1601-0660"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Satu-Marja M\u00e4kel\u00e4","raw_affiliation_strings":["VTT Technical Research Center of Finland, Oulu, Finland","VTT, Technical Research Center of Finland, Oulu, Finland"],"affiliations":[{"raw_affiliation_string":"VTT Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]},{"raw_affiliation_string":"VTT, Technical Research Center of Finland, Oulu, Finland","institution_ids":["https://openalex.org/I87653560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5087629198"],"corresponding_institution_ids":["https://openalex.org/I2738502077"],"apc_list":null,"apc_paid":null,"fwci":0.3798,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60130293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"120"},"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":0.9993000030517578,"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":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8396188020706177},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6403841972351074},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.5371596813201904},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5357993841171265},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.494081050157547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46296313405036926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43548697233200073},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.38566315174102783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3611634075641632},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3601749539375305},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.33212804794311523},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.2891544699668884}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8396188020706177},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6403841972351074},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.5371596813201904},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5357993841171265},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.494081050157547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46296313405036926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43548697233200073},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.38566315174102783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3611634075641632},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3601749539375305},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.33212804794311523},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2891544699668884}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1460096.1460116","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1460096.1460116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM international conference on Multimedia information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.7177","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.7177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/heln/Publications/MIR_Helen.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.47999998927116394},{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W21391682","https://openalex.org/W134184673","https://openalex.org/W1482605500","https://openalex.org/W2009049512","https://openalex.org/W2014915963","https://openalex.org/W2046955072","https://openalex.org/W2074519486","https://openalex.org/W2115717467","https://openalex.org/W2127144933","https://openalex.org/W2131981197","https://openalex.org/W2143714442","https://openalex.org/W2148671289","https://openalex.org/W2152335417","https://openalex.org/W2159104102","https://openalex.org/W2977970220","https://openalex.org/W6605549694"],"related_works":["https://openalex.org/W2350061705","https://openalex.org/W4248908904","https://openalex.org/W4382119215","https://openalex.org/W4237593738","https://openalex.org/W4230436760","https://openalex.org/W2363106653","https://openalex.org/W4251828160","https://openalex.org/W296599067","https://openalex.org/W2385192540","https://openalex.org/W4251849079"],"abstract_inverted_index":{"State-of-the-art":[0],"automatic":[1],"analysis":[2,66,70,128],"tools":[3,27,129],"for":[4,28,63,130],"personal":[5],"audio":[6,29,42,50,139],"con-tent":[7],"management":[8,26],"are":[9],"discussed":[10],"in":[11,162],"this":[12],"paper.":[13],"Our":[14],"main":[15,49,99],"target":[16],"is":[17,102,160],"to":[18,105],"create":[19],"a":[20,60,86],"system,":[21],"which":[22,32],"has":[23],"several":[24],"co-operating":[25],"database":[30,146],"and":[31,55,57,81,89,109,142],"improve":[33],"the":[34,97,116,125,135,154,158],"results":[35,151],"of":[36,119,127,137,157],"each":[37],"other.":[38],"Bayesian":[39,75],"networks":[40],"based":[41,78],"classification":[43,46],"algorithm":[44,83,92,144],"provides":[45],"into":[47],"four":[48],"classes":[51,100,132],"(silence,":[52],"speech,":[53],"music,":[54],"noise)":[56],"serves":[58],"as":[59],"first":[61],"step":[62],"other":[64,98],"subsequent":[65],"tools.":[67],"For":[68,96,123],"speech":[69],"we":[71,133],"propose":[72,134],"an":[73],"improved":[74],"information":[76],"criterion":[77],"speaker":[79],"segmen-tation":[80],"clustering":[82,147],"applying":[84],"also":[85],"combined":[87,155],"gender":[88],"emotion":[90],"detection":[91],"utilizing":[93],"prosodic":[94],"features.":[95],"it":[101],"often":[103],"hard":[104],"device":[106],"any":[107],"general":[108],"well":[110],"functional":[111],"pre-categorization":[112],"that":[113,153],"would":[114],"fit":[115],"unforesee-able":[117],"types":[118],"user":[120],"recorded":[121],"data.":[122],"compensating":[124],"absence":[126],"these":[131],"use":[136,156],"efficient":[138],"similarity":[140],"measure":[141],"query-by-example":[143],"with":[145],"capabilities.":[148],"The":[149],"experimental":[150],"show":[152],"algorithms":[159],"feasible":[161],"practice.":[163]},"counts_by_year":[{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
