{"id":"https://openalex.org/W2115453400","doi":"https://doi.org/10.1109/icassp.2004.1326834","title":"Improve audio representation by using feature structure patterns","display_name":"Improve audio representation by using feature structure patterns","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2115453400","doi":"https://doi.org/10.1109/icassp.2004.1326834","mag":"2115453400"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5114723550","display_name":"Rui Cai","orcid":"https://orcid.org/0009-0006-2823-3051"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"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":["5/F Sigma Center, Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"5/F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397026","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1991-119X"},"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":["5/F Sigma Center, Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"5/F Sigma Center, Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lian-Hong Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114723550"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.5238,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89742207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"4","issue":null,"first_page":"iv","last_page":"345"},"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":0.9990000128746033,"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":0.9947999715805054,"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":0.7817448377609253},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7140202522277832},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6497637629508972},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5636090040206909},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5216948390007019},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.49984145164489746},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48684900999069214},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4861025810241699},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.47806838154792786},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43435773253440857},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39905670285224915},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.27016401290893555},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.058395057916641235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817448377609253},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7140202522277832},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6497637629508972},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5636090040206909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5216948390007019},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.49984145164489746},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48684900999069214},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4861025810241699},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.47806838154792786},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43435773253440857},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39905670285224915},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.27016401290893555},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.058395057916641235},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W161049316","https://openalex.org/W1545046063","https://openalex.org/W1971784203","https://openalex.org/W1985014571","https://openalex.org/W1996297604","https://openalex.org/W2042591571","https://openalex.org/W2074188409","https://openalex.org/W2131981197","https://openalex.org/W2146171479","https://openalex.org/W2319660501","https://openalex.org/W2330519819","https://openalex.org/W4231464474","https://openalex.org/W4298374011","https://openalex.org/W6606484279","https://openalex.org/W6661122342"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W1611900921","https://openalex.org/W3110605476","https://openalex.org/W2766269877","https://openalex.org/W2100375615"],"abstract_inverted_index":{"Although":[0],"statistical":[1],"characteristics":[2,49],"of":[3,50,87],"audio":[4,10,15,60,95],"features":[5],"are":[6,56,80],"widely":[7],"used":[8],"for":[9],"representation":[11],"in":[12,39],"most":[13],"current":[14],"analysis":[16],"systems":[17],"and":[18,34,53,76],"have":[19],"been":[20],"proved":[21],"to":[22,37,58],"be":[23],"effective,":[24],"they":[25],"only":[26],"utilize":[27],"the":[28,46],"average":[29],"feature":[30],"variations":[31],"over":[32],"time,":[33],"thus":[35],"lead":[36],"ambiguities":[38],"some":[40],"cases.":[41],"Structure":[42],"patterns,":[43,67],"which":[44],"describe":[45],"representative":[47],"structure":[48,66],"both":[51],"temporal":[52],"spectral":[54,73],"features,":[55],"proposed":[57,81],"improve":[59],"representation.":[61],"In":[62],"this":[63],"paper,":[64],"three":[65],"including":[68],"energy":[69],"envelope":[70],"pattern,":[71,79],"sub-band":[72],"shape":[74],"pattern":[75],"harmonicity":[77],"prominence":[78],"or":[82],"refined,":[83],"as":[84],"successive":[85],"development":[86],"our":[88],"previous":[89],"work.":[90],"Evaluations":[91],"on":[92],"a":[93],"content-based":[94],"retrieval":[96],"system":[97],"with":[98],"more":[99],"than":[100],"1500":[101],"clips":[102],"showed":[103],"very":[104],"encouraging":[105],"results.":[106]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
