{"id":"https://openalex.org/W2036945436","doi":"https://doi.org/10.1142/s0218001405004290","title":"CONTENT-BASED AUDIO RETRIEVAL BASED ON GABOR WAVELET FILTERING","display_name":"CONTENT-BASED AUDIO RETRIEVAL BASED ON GABOR WAVELET FILTERING","publication_year":2005,"publication_date":"2005-09-01","ids":{"openalex":"https://openalex.org/W2036945436","doi":"https://doi.org/10.1142/s0218001405004290","mag":"2036945436"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001405004290","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405004290","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":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.15981875,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":"06","first_page":"823","last_page":"837"},"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":0.9955000281333923,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9783999919891357,"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":0.8293383121490479},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.593338668346405},{"id":"https://openalex.org/keywords/gabor-wavelet","display_name":"Gabor wavelet","score":0.5879119038581848},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5388708710670471},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.5325552225112915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5098320841789246},{"id":"https://openalex.org/keywords/gabor-filter","display_name":"Gabor filter","score":0.46686816215515137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4635006785392761},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45318976044654846},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4508235454559326},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43645548820495605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41933491826057434},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.3614107668399811},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35015812516212463},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2805909514427185},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.14965876936912537},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1277824342250824},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1203269362449646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08044043183326721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293383121490479},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.593338668346405},{"id":"https://openalex.org/C136902061","wikidata":"https://www.wikidata.org/wiki/Q16981559","display_name":"Gabor wavelet","level":5,"score":0.5879119038581848},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5388708710670471},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.5325552225112915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5098320841789246},{"id":"https://openalex.org/C2779883129","wikidata":"https://www.wikidata.org/wiki/Q2447890","display_name":"Gabor filter","level":3,"score":0.46686816215515137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4635006785392761},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45318976044654846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4508235454559326},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43645548820495605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41933491826057434},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.3614107668399811},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35015812516212463},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2805909514427185},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.14965876936912537},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1277824342250824},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1203269362449646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08044043183326721},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0218001405004290","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001405004290","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:10.1.1.419.8843","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.419.8843","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/J46.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4300000071525574,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W9359371","https://openalex.org/W152093514","https://openalex.org/W1485800236","https://openalex.org/W1567997379","https://openalex.org/W1570513731","https://openalex.org/W1574901103","https://openalex.org/W1620668332","https://openalex.org/W1986736663","https://openalex.org/W2027518030","https://openalex.org/W2032360374","https://openalex.org/W2043843997","https://openalex.org/W2046134527","https://openalex.org/W2057613716","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2098981776","https://openalex.org/W2111331420","https://openalex.org/W2115101691","https://openalex.org/W2125148312","https://openalex.org/W2134224259","https://openalex.org/W2221009957","https://openalex.org/W2294317068","https://openalex.org/W2973818247","https://openalex.org/W4233392025","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1710806717","https://openalex.org/W2394322125","https://openalex.org/W2355521768","https://openalex.org/W2070838085","https://openalex.org/W2055938957","https://openalex.org/W4210684035","https://openalex.org/W2374740620","https://openalex.org/W2902714807","https://openalex.org/W2803685646","https://openalex.org/W2495360253"],"abstract_inverted_index":{"Rapid":[0],"increase":[1],"in":[2,47,79,90],"the":[3,30,52,112,122,138,148],"amount":[4],"of":[5,42,105,115,141],"audio":[6,19,48,61,100,109,158],"data":[7],"and":[8,63],"especially":[9],"music":[10,45,74,77],"collections":[11],"demand":[12],"an":[13,60,99],"efficient":[14],"method":[15,38,95,150],"to":[16,54,133],"automatically":[17],"retrieve":[18,64],"objects":[20],"based":[21,28,120],"on":[22,29,121,137],"its":[23],"content.":[24],"In":[25],"this":[26],"paper,":[27],"Gabor":[31,123],"wavelet":[32,124],"features,":[33],"we":[34],"will":[35,96],"propose":[36],"a":[37,56,73,80,127],"for":[39,157],"content-based":[40],"retrieval":[41],"perceptually":[43,65],"similar":[44,66,76],"pieces":[46],"documents.":[49],"It":[50],"allows":[51],"user":[53],"select":[55],"reference":[57],"passage":[58],"within":[59,72],"file":[62],"passages":[67],"such":[68],"as":[69],"repeating":[70],"phrases":[71],"piece,":[75],"clips":[78],"database":[81],"or":[82,89],"one":[83],"song":[84],"sung":[85],"by":[86],"different":[87,91],"persons":[88],"languages.":[92],"The":[93],"proposed":[94,149],"first":[97],"divide":[98],"stream":[101],"into":[102],"clips,":[103],"each":[104,116],"which":[106],"contains":[107],"one-second":[108],"information.":[110],"Then,":[111],"frame-based":[113],"features":[114],"clip":[117],"are":[118],"extracted":[119],"filters.":[125],"Finally,":[126],"similarity":[128],"measuring":[129],"technique":[130],"is":[131],"provided":[132],"perform":[134],"pattern":[135],"matching":[136],"resulting":[139],"sequences":[140],"feature":[142],"vectors.":[143],"Experimental":[144],"results":[145],"show":[146],"that":[147],"can":[151],"achieve":[152],"over":[153],"96%":[154],"accuracy":[155],"rate":[156],"retrieval.":[159]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
