{"id":"https://openalex.org/W93454604","doi":null,"title":"Classifying motion picture audio","display_name":"Classifying motion picture audio","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W93454604","mag":"93454604"},"language":"en","primary_location":{"id":"pmh:oai:ntnuopen.ntnu.no:11250/144070","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11250/144070","pdf_url":"http://hdl.handle.net/11250/144070","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11250/144070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013577140","display_name":"Eirik Gustavsen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Eirik Gustavsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5013577140"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":9.999999747378752e-05,"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":0.0,"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/audio-classification","display_name":"audio classification","score":0.5619999766349792},{"id":"https://openalex.org/keywords/environmental-sounds","display_name":"environmental sounds","score":0.5690000057220459},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.5550000071525574},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.7089999914169312},{"id":"https://openalex.org/keywords/k-nearest-neighbors","display_name":"k-nearest neighbors","score":0.8059999942779541},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.7689999938011169},{"id":"https://openalex.org/keywords/zero-crossing-rate","display_name":"zero-crossing rate","score":0.8840000033378601},{"id":"https://openalex.org/keywords/groundhog-day","display_name":"Groundhog Day","score":0.6039999723434448},{"id":"https://openalex.org/keywords/objective-quality-metrics","display_name":"objective quality metrics","score":0.3240000009536743}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5250261425971985},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5105396509170532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4977462589740753},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3433845043182373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31079530715942383},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29101669788360596}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:ntnuopen.ntnu.no:11250/144070","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11250/144070","pdf_url":"http://hdl.handle.net/11250/144070","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"},{"id":"mag:93454604","doi":null,"is_oa":false,"landing_page_url":"https://brage.bibsys.no/xmlui/handle/11250/144070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:ntnuopen.ntnu.no:11250/144070","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/11250/144070","pdf_url":"http://hdl.handle.net/11250/144070","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W93454604.pdf","grobid_xml":"https://content.openalex.org/works/W93454604.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W24912070","https://openalex.org/W44244862","https://openalex.org/W84813673","https://openalex.org/W131293899","https://openalex.org/W156361483","https://openalex.org/W1539718938","https://openalex.org/W1545046063","https://openalex.org/W1965664780","https://openalex.org/W1970308149","https://openalex.org/W1993625798","https://openalex.org/W2009928121","https://openalex.org/W2027518030","https://openalex.org/W2039275978","https://openalex.org/W2044222806","https://openalex.org/W2052384514","https://openalex.org/W2062526508","https://openalex.org/W2074188409","https://openalex.org/W2078306367","https://openalex.org/W2095681812","https://openalex.org/W2096686458","https://openalex.org/W2103869314","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2110215948","https://openalex.org/W2120515242","https://openalex.org/W2121151646","https://openalex.org/W2128838222","https://openalex.org/W2129116144","https://openalex.org/W2129244720","https://openalex.org/W2131981197","https://openalex.org/W2147174722","https://openalex.org/W2148154194","https://openalex.org/W2149054612","https://openalex.org/W2168441989","https://openalex.org/W2343867458","https://openalex.org/W2408660648","https://openalex.org/W3181498640","https://openalex.org/W4250499635"],"related_works":["https://openalex.org/W6903531028","https://openalex.org/W2110215948","https://openalex.org/W2029261284","https://openalex.org/W2991776622","https://openalex.org/W2198868643","https://openalex.org/W2168858660","https://openalex.org/W2973189317","https://openalex.org/W2955618890","https://openalex.org/W3124209769","https://openalex.org/W2369408286"],"abstract_inverted_index":{"ENGELSK:\\nClassification":[0],"of":[1,5,23,60,63,71,86,179,187,284,331,338,358],"the":[2,21,113,131,182,203,217,224,231,237,252,266,285,299,320,324,332,339,341,350],"audio":[3,11,46,52,64,321],"track,":[4],"a":[6,141,147,177],"motion":[7],"picture,":[8],"into":[9],"traditional":[10],"classes":[12],"is":[13,20,134,215,334],"a\\nchallenging":[14],"task.":[15],"The":[16,150,174,241],"reason":[17],"for":[18,43,58,154,336],"this":[19,61,364],"amount":[22],"mixed":[24,51,301],"content.":[25,53],"Speech":[26],"has":[27,35,176],"often\\nbackground":[28],"music":[29,34,258,267],"or":[30,39],"environmental":[31,197],"sounds,":[32],"and":[33,56,79,138,229,248,305],"often":[36],"background":[37,158,193,257],"environmental\\nsounds":[38,194],"speech.":[40,282],"Traditional":[41],"methods":[42,55],"separating":[44,155,293],"clear":[45,196,294,314],"classes\\nhave":[47],"limited":[48],"performance":[49],"on":[50,236,363],"New":[54],"tools":[57],"automatic\\nclassification":[59],"type":[62],"are":[65],"therefore":[66],"needed.":[67],"This":[68],"project":[69],"investigates\\ncombinations":[70],"low":[72,286],"level":[73,287],"descriptors,":[74],"dimensionality":[75],"reduction":[76],"by":[77],"PCA":[78,225],"classification\\nby":[80],"KNN.":[81],"A":[82,316,356],"feature":[83],"set":[84],"consisting":[85],"Audio":[87,90],"Power":[88],"(AP),":[89],"Wave":[91],"Form":[92],"(AWF),":[93],"Root-\\nMean-Square":[94],"(RMS),":[95],"Short":[96],"Time":[97],"Energy":[98,102],"(STE),":[99],"Low":[100],"Short-Time":[101],"Ratio,":[103],"Zero-\\nCrossing":[104],"Rate":[105,109],"(ZCR),":[106],"High":[107],"Zero-Crossing":[108],"Ratio":[110],"(HZCRR)":[111],"in":[112,130,216,298],"time":[114,183],"domain":[115,133],"and\\nAudio":[116],"Spectrum":[117,127],"Centroid":[118],"(ASC),":[119],"Fundamental":[120],"Frequency":[121,124,211],"(FuF),":[122],"Mel,":[123],"Cepstral\\nCoefficients":[125],"(MFCC),":[126],"Flux":[128],"(SF)":[129],"frequency":[132,218],"extracted":[135],"on\\n30ms":[136],"windows":[137],"integrated":[139],"over":[140],"1.2":[142],"second":[143],"frame":[144],"to":[145,189,201,250,270,278,308],"yield":[146],"23-dimmensional":[148],"feature\\nvector.":[149],"most":[151],"suitable":[152,185],"combination":[153,175,186],"speech":[156,191,255,310],"from":[157,181,195,243,313,323],"music\\nwere;":[159],"AP,":[160],"ASC,":[161],"AWF,":[162],"STE,":[163],"RMS,":[164],"SF,":[165],"fourth":[166],"MFCC,":[167],"AP(min":[168],"scalar),":[169],"ZCR(min":[170],"scalar)":[171],"and\\nSTE(min":[172],"scalar).":[173],"majority":[178],"descriptors":[180,288],"domain.\\nMost":[184],"LLDs":[188],"separate":[190,309],"with":[192,256,311],"sounds":[198],"was":[199,345,352,360],"found":[200],"be":[202,271,279],"1th,":[204],"4th,":[205],"5th,":[206],"6th,":[207],"8th":[208],"and\\n9th":[209],"Mel":[210],"cepstran":[212],"coefficients.":[213],"MFCC":[214],"domain.":[219],"Best":[220],"results\\nwere":[221],"achieved":[222],"when":[223,230,292],"returned":[226],"3":[227],"dimensions,":[228],"KNN":[232],"classified":[233,280],"the\\nsamples":[234],"based":[235,362],"4":[238],"closest":[239],"neighbors.":[240],"results":[242],"testing":[244],"different":[245],"mixtures":[246],"of\\nspeech":[247],"music,":[249],"find":[251],"boundary":[253],"where":[254],"no":[259],"longer\\nis":[260],"categorized":[261],"as":[262,281],"speech,":[263],"showed":[264],"that":[265],"signal":[268,277],"had":[269],"minimum":[272],"8":[273],"dB":[274],"below":[275],"the\\nspeech":[276],"Some":[283],"which":[289],"traditionally\\nperforms":[290],"well":[291],"classes,":[295],"performed":[296],"poorly":[297],"experiments\\nwith":[300],"classes.":[302],"Especially":[303],"ZCR":[304],"FuF":[306],"failed":[307],"background\\nmusic":[312],"music.":[315],"final":[317],"experiment":[318],"classifies":[319],"track":[322],"motion\\npicture":[325],"\u2019Groundhog":[326],"Day\u2019.":[327],"First":[328],"80":[329],"percent":[330,344],"movie":[333],"used":[335],"training":[337],"KNN,\\nand":[340],"remaining":[342],"20":[343],"classified.":[346,355],"After":[347],"post":[348],"processing":[349],"result":[351],"76.9\\npercent":[353],"correctly":[354],"table":[357],"content":[359],"then":[361],"classification.":[365]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}