{"id":"https://openalex.org/W2107229664","doi":"https://doi.org/10.1142/s0218001405003958","title":"A NEW APPROACH FOR CLASSIFICATION OF GENERIC AUDIO DATA","display_name":"A NEW APPROACH FOR CLASSIFICATION OF GENERIC AUDIO DATA","publication_year":2005,"publication_date":"2005-02-01","ids":{"openalex":"https://openalex.org/W2107229664","doi":"https://doi.org/10.1142/s0218001405003958","mag":"2107229664"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001405003958","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405003958","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-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/A5028721935","display_name":"RUEI-SHIANG LIN","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"RUEI-SHIANG LIN","raw_affiliation_strings":["Department of Computer and Information Science, National Chiao Tung University, 1001 Ta Hsueh Rd., Hsinchu, Taiwan 30050, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, National Chiao Tung University, 1001 Ta Hsueh Rd., Hsinchu, Taiwan 30050, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002645149","display_name":"Ling\u2010Hwei Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"LING-HWEI CHEN","raw_affiliation_strings":["Department of Computer and Information Science, National Chiao Tung University, 1001 Ta Hsueh Rd., Hsinchu, Taiwan 30050, R.O.C"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, National Chiao Tung University, 1001 Ta Hsueh Rd., Hsinchu, Taiwan 30050, R.O.C","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.3207,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.5860533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":"01","first_page":"63","last_page":"78"},"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":0.9983000159263611,"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":0.9886000156402588,"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":0.8112834692001343},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7463746666908264},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.7314468622207642},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5584050416946411},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5561363697052002},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.47960078716278076},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.45270204544067383},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43920913338661194},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3920888304710388},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.38342732191085815},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3629855513572693},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3578346371650696},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3455761671066284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32715946435928345},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.25166386365890503}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112834692001343},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7463746666908264},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.7314468622207642},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5584050416946411},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5561363697052002},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.47960078716278076},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.45270204544067383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43920913338661194},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3920888304710388},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.38342732191085815},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3629855513572693},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3578346371650696},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3455761671066284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32715946435928345},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25166386365890503},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218001405003958","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405003958","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.4702","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.4702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://debut.cis.nctu.edu.tw/Publications/pdfs/J44.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W9359371","https://openalex.org/W143678519","https://openalex.org/W1480813574","https://openalex.org/W1570513731","https://openalex.org/W1620668332","https://openalex.org/W1986736663","https://openalex.org/W2032360374","https://openalex.org/W2046134527","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2106055371","https://openalex.org/W2115101691","https://openalex.org/W2124660252","https://openalex.org/W2128838222","https://openalex.org/W2144345993","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1996547972","https://openalex.org/W1975359510","https://openalex.org/W1611900921","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W27741130","https://openalex.org/W3110605476","https://openalex.org/W1620668332"],"abstract_inverted_index":{"The":[0,152],"existing":[1],"audio":[2,35,55,75,97,102,132,184],"retrieval":[3,30],"systems":[4,12,26],"fall":[5],"into":[6,99],"one":[7],"of":[8,17,34,54,131,144,169,178],"two":[9],"categories:":[10],"single-domain":[11,39],"that":[13,27],"can":[14,73,82,155],"accept":[15],"data":[16,56,185],"only":[18],"a":[19,38,44,64,91,129,147],"single":[20],"type":[21],"(e.g.":[22],"speech)":[23],"or":[24],"multiple-domain":[25,45,65],"offer":[28],"content-based":[29,159],"for":[31,128,139,149,182],"multiple":[32],"types":[33,53,103],"data.":[36],"Since":[37],"system":[40,46,66],"has":[41],"limited":[42],"applications,":[43],"will":[47,57,62,89],"be":[48,69,83,156],"more":[49,179],"useful.":[50],"However,":[51],"different":[52,59],"have":[58],"properties,":[60],"this":[61,86,170],"make":[63,123],"harder":[67],"to":[68,95,122,158],"developed.":[70],"If":[71],"we":[72,88,134],"classify":[74,96],"information":[76],"in":[77],"advance,":[78],"the":[79,124,163,165],"above":[80],"problems":[81],"solved.":[84],"In":[85,120,162],"paper,":[87],"propose":[90],"real-time":[92],"classification":[93],"method":[94,126,171],"signals":[98],"several":[100],"basic":[101],"such":[104],"as":[105],"pure":[106],"speech,":[107],"music,":[108],"song,":[109],"speech":[110,115],"with":[111,116],"music":[112],"background,":[113],"and":[114,167],"environmental":[117],"noise":[118],"background.":[119],"order":[121],"proposed":[125,153],"robust":[127],"variety":[130],"sources,":[133],"use":[135],"Bayesian":[136],"decision":[137],"function":[138],"multivariable":[140],"Gaussian":[141],"distribution":[142],"instead":[143],"manually":[145],"adjusting":[146],"threshold":[148],"each":[150],"discriminator.":[151],"approach":[154],"applied":[157],"audio/video":[160],"retrieval.":[161],"experiment,":[164],"efficiency":[166],"effectiveness":[168],"are":[172],"shown":[173],"by":[174],"an":[175],"accuracy":[176],"rate":[177],"than":[180],"96%":[181],"general":[183],"classification.":[186]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}