{"id":"https://openalex.org/W2160452081","doi":"https://doi.org/10.1142/s0218001405004289","title":"A NEW APPROACH FOR AUDIO CLASSIFICATION AND SEGMENTATION USING GABOR WAVELETS AND FISHER LINEAR DISCRIMINATOR","display_name":"A NEW APPROACH FOR AUDIO CLASSIFICATION AND SEGMENTATION USING GABOR WAVELETS AND FISHER LINEAR DISCRIMINATOR","publication_year":2005,"publication_date":"2005-09-01","ids":{"openalex":"https://openalex.org/W2160452081","doi":"https://doi.org/10.1142/s0218001405004289","mag":"2160452081"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001405004289","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405004289","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"],"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":true,"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"],"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":2,"corresponding_author_ids":["https://openalex.org/A5002645149"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.3179,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61492653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"19","issue":"06","first_page":"807","last_page":"822"},"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":0.998199999332428,"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":0.9593999981880188,"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":0.747374415397644},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.677055835723877},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.656035304069519},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6099119782447815},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6097646951675415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5291048884391785},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5250422954559326},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5089621543884277},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5082449316978455},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49532976746559143},{"id":"https://openalex.org/keywords/gabor-wavelet","display_name":"Gabor wavelet","score":0.485227108001709},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4554566442966461},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.40467676520347595},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.24238193035125732},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.2083365023136139},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.2024824619293213},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.07346990704536438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.747374415397644},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.677055835723877},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.656035304069519},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6099119782447815},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6097646951675415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5291048884391785},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5250422954559326},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5089621543884277},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5082449316978455},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49532976746559143},{"id":"https://openalex.org/C136902061","wikidata":"https://www.wikidata.org/wiki/Q16981559","display_name":"Gabor wavelet","level":5,"score":0.485227108001709},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4554566442966461},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.40467676520347595},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.24238193035125732},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.2083365023136139},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.2024824619293213},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.07346990704536438},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001405004289","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405004289","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W9359371","https://openalex.org/W143678519","https://openalex.org/W1480813574","https://openalex.org/W1567997379","https://openalex.org/W1570513731","https://openalex.org/W1620668332","https://openalex.org/W1986736663","https://openalex.org/W2032360374","https://openalex.org/W2043843997","https://openalex.org/W2046134527","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2106055371","https://openalex.org/W2115101691","https://openalex.org/W2121647436","https://openalex.org/W2124660252","https://openalex.org/W2125148312","https://openalex.org/W2128838222","https://openalex.org/W2144345993","https://openalex.org/W2294317068","https://openalex.org/W2973818247","https://openalex.org/W4233392025","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4224918993","https://openalex.org/W2109142991","https://openalex.org/W1911859126","https://openalex.org/W46679383","https://openalex.org/W1781713806","https://openalex.org/W2350061705","https://openalex.org/W2040013831","https://openalex.org/W2112616324","https://openalex.org/W2717715803","https://openalex.org/W2106826515"],"abstract_inverted_index":{"Rapid":[0],"increase":[1],"in":[2,175],"the":[3,28,108,127,135,159],"amount":[4],"of":[5,51,64,115,162],"audio":[6,17,33,46,55,116,172,176],"data":[7],"demands":[8],"an":[9,32,45],"efficient":[10],"method":[11,37,41,110,137],"to":[12,101,106,123],"automatically":[13],"segment":[14],"or":[15,67],"classify":[16],"stream":[18,47],"based":[19,26],"on":[20,27],"its":[21],"content.":[22],"In":[23,104],"this":[24],"paper,":[25],"Gabor":[29],"wavelet":[30],"features,":[31],"classification":[34],"and":[35,74,85,146,149],"segmentation":[36],"is":[38,60,99],"proposed.":[39],"This":[40],"will":[42],"first":[43],"divide":[44],"into":[48],"clips,":[49,164],"each":[50,58],"which":[52],"contains":[53],"one-second":[54],"information.":[56],"Then,":[57],"clip":[59],"classified":[61],"as":[62],"one":[63],"two":[65],"classes":[66,71],"five":[68,93],"classes.":[69,94],"Two":[70],"contain":[72],"speech":[73,81,86,145],"music;":[75],"pure":[76,78],"speech,":[77],"music,":[79],"song,":[80],"with":[82,87,126],"music":[83,147],"background,":[84],"environmental":[88],"noise":[89],"background":[90],"are":[91],"for":[92,112,144,153],"Finally,":[95],"a":[96,113,154],"merge":[97],"technique":[98],"provided":[100],"do":[102],"segmentation.":[103],"order":[105],"make":[107],"proposed":[109,136],"robust":[111],"variety":[114],"sources,":[117],"we":[118,165],"use":[119],"Fisher":[120],"Linear":[121],"Discriminator":[122],"obtain":[124],"features":[125],"highest":[128],"discriminative":[129],"ability.":[130],"Experimental":[131],"results":[132],"show":[133],"that":[134],"can":[138,166],"achieve":[139],"over":[140],"98%":[141],"accuracy":[142],"rate":[143],"discrimination,":[148],"more":[150,169],"than":[151,170],"95%":[152,171],"five-way":[155],"discrimination.":[156],"By":[157],"checking":[158],"class":[160],"types":[161],"adjacent":[163],"also":[167],"identify":[168],"scene":[173],"breaks":[174],"sequence.":[177]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}