{"id":"https://openalex.org/W2151218017","doi":"https://doi.org/10.1109/icme.2009.5202574","title":"A two phase method for general audio segmentation","display_name":"A two phase method for general audio segmentation","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2151218017","doi":"https://doi.org/10.1109/icme.2009.5202574","mag":"2151218017"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2009.5202574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","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/A5090771862","display_name":"Jessie Xin Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jessie Xin Zhang","raw_affiliation_strings":["School of Computing and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007734757","display_name":"Jacqueline Whalley","orcid":"https://orcid.org/0000-0001-7633-5200"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jacqueline Whalley","raw_affiliation_strings":["School of Computing and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I39854758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103183670","display_name":"Stephen Brooks","orcid":"https://orcid.org/0000-0002-7473-5830"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Stephen Brooks","raw_affiliation_strings":["Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0715,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.78041995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"626","last_page":"629"},"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":0.9994000196456909,"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":0.9894999861717224,"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":0.8085204362869263},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6906218528747559},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5993452072143555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5693179368972778},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5269708633422852},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5150017738342285},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5034176707267761},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.484811931848526},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4665752351284027},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4595261216163635},{"id":"https://openalex.org/keywords/digital-audio","display_name":"Digital audio","score":0.4396134316921234},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4270116686820984},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2910916805267334},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2034347951412201},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.19170555472373962},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.1732339859008789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8085204362869263},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6906218528747559},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5993452072143555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5693179368972778},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5269708633422852},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5150017738342285},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5034176707267761},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.484811931848526},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4665752351284027},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4595261216163635},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.4396134316921234},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4270116686820984},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2910916805267334},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2034347951412201},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.19170555472373962},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.1732339859008789}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2009.5202574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2009.5202574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.156.9449","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.156.9449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cs.dal.ca/~sbrooks/projects/AudioVis/ATwoPhaseMethodForGeneralAudioSegmentation.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W325132576","https://openalex.org/W1482605500","https://openalex.org/W1492953952","https://openalex.org/W1957105039","https://openalex.org/W1966818380","https://openalex.org/W2008765103","https://openalex.org/W2018097742","https://openalex.org/W2084134149","https://openalex.org/W2110458017","https://openalex.org/W2127805579","https://openalex.org/W2137937696","https://openalex.org/W2138406164","https://openalex.org/W2144326614","https://openalex.org/W2151305614","https://openalex.org/W3017143921","https://openalex.org/W3148083387","https://openalex.org/W6628911050","https://openalex.org/W6629394414","https://openalex.org/W6652214876"],"related_works":["https://openalex.org/W2970176078","https://openalex.org/W2098934641","https://openalex.org/W2289868279","https://openalex.org/W4254699594","https://openalex.org/W1975359510","https://openalex.org/W2363106653","https://openalex.org/W1496727373","https://openalex.org/W2020952589","https://openalex.org/W3110605476","https://openalex.org/W1620668332"],"abstract_inverted_index":{"This":[0,112],"paper":[1],"presents":[2],"a":[3,26,47,121],"model-free":[4],"and":[5,120,165],"training-free":[6],"two-phase":[7,113],"method":[8,77,114,126],"for":[9,108,137],"audio":[10,16,33,36,53,69,93,138,155,160],"segmentation":[11,31,132],"that":[12,87,142],"separates":[13,32],"monophonic":[14],"heterogeneous":[15],"files":[17],"into":[18,35],"acoustically":[19],"homogeneous":[20],"regions":[21,82],"where":[22],"each":[23],"region":[24],"contains":[25],"single":[27],"sound.":[28],"A":[29],"rough":[30],"input":[34,110],"clips":[37],"based":[38,50],"on":[39,51],"silence":[40],"detection":[41,76],"in":[42,55,67,83,91,153],"the":[43,56,61,68,84,92,98,105,109],"time":[44],"domain.":[45],"Then":[46],"self-similarity":[48],"matrix,":[49],"selected":[52],"features":[54],"frequency":[57],"domain":[58],"to":[59,80,103],"discover":[60],"level":[62],"of":[63,97],"similarity":[64,85],"between":[65],"frames":[66],"clip,":[70],"is":[71,78,115],"calculated.":[72],"Subsequently":[73],"an":[74,149],"edge":[75],"used":[79],"find":[81],"image":[86],"determine":[88],"plausible":[89],"sounds":[90],"clip.":[94],"The":[95,125],"results":[96,133],"two":[99],"phases":[100],"are":[101],"combined":[102],"form":[104],"final":[106],"boundaries":[107],"audio.":[111],"evaluated":[116],"using":[117],"established":[118],"methods":[119,136],"standard":[122],"non-musical":[123],"database.":[124],"reported":[127],"here":[128],"offers":[129],"more":[130],"accurate":[131],"than":[134],"existing":[135],"segmentation.":[139],"We":[140],"propose":[141],"this":[143],"approach":[144],"could":[145],"be":[146],"adapted":[147],"as":[148,159],"efficient":[150],"preprocessing":[151],"stage":[152],"other":[154],"processing":[156],"systems":[157],"such":[158],"retrieval,":[161],"classification,":[162],"music":[163],"analysis":[164],"summarization.":[166]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}