{"id":"https://openalex.org/W1987426045","doi":"https://doi.org/10.1155/2009/239892","title":"A Decision-Tree-Based Algorithm for Speech/Music Classification and Segmentation","display_name":"A Decision-Tree-Based Algorithm for Speech/Music Classification and Segmentation","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1987426045","doi":"https://doi.org/10.1155/2009/239892","mag":"1987426045"},"language":"en","primary_location":{"id":"doi:10.1155/2009/239892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/239892","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1155/2009/239892","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053447731","display_name":"Yizhar Lavner","orcid":"https://orcid.org/0000-0002-2865-0465"},"institutions":[{"id":"https://openalex.org/I68147069","display_name":"Tel Hai Academic College","ror":"https://ror.org/009st3569","country_code":"IL","type":"education","lineage":["https://openalex.org/I68147069"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Yizhar Lavner","raw_affiliation_strings":["Department of Computer Science, Tel-Hai College, Tel-Hai, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tel-Hai College, Tel-Hai, Israel","institution_ids":["https://openalex.org/I68147069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051589781","display_name":"Dima Ruinskiy","orcid":null},"institutions":[{"id":"https://openalex.org/I68147069","display_name":"Tel Hai Academic College","ror":"https://ror.org/009st3569","country_code":"IL","type":"education","lineage":["https://openalex.org/I68147069"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dima Ruinskiy","raw_affiliation_strings":["Department of Computer Science, Tel-Hai College, Tel-Hai, Israel and Israeli Development Center, Intel Corporation, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tel-Hai College, Tel-Hai, Israel and Israeli Development Center, Intel Corporation, Haifa, Israel","institution_ids":["https://openalex.org/I68147069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053447731"],"corresponding_institution_ids":["https://openalex.org/I68147069"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.142,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.86337132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"2009","issue":null,"first_page":"1","last_page":"14"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.988099992275238,"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/decision-tree","display_name":"Decision tree","score":0.7002760171890259},{"id":"https://openalex.org/keywords/decision-tree-learning","display_name":"Decision tree learning","score":0.6026806235313416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5793713331222534},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5585076212882996},{"id":"https://openalex.org/keywords/id3-algorithm","display_name":"ID3 algorithm","score":0.5379631519317627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5220691561698914},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.46382442116737366},{"id":"https://openalex.org/keywords/incremental-decision-tree","display_name":"Incremental decision tree","score":0.4358074963092804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4148719906806946},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4069632589817047},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34656980633735657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1873946487903595}],"concepts":[{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.7002760171890259},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.6026806235313416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5793713331222534},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5585076212882996},{"id":"https://openalex.org/C183931066","wikidata":"https://www.wikidata.org/wiki/Q1653378","display_name":"ID3 algorithm","level":5,"score":0.5379631519317627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5220691561698914},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46382442116737366},{"id":"https://openalex.org/C10229987","wikidata":"https://www.wikidata.org/wiki/Q17083028","display_name":"Incremental decision tree","level":4,"score":0.4358074963092804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4148719906806946},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4069632589817047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34656980633735657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1873946487903595},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1155/2009/239892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/239892","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4ca09bffacd04225b7b980f75b1dab07","is_oa":false,"landing_page_url":"https://doaj.org/article/4ca09bffacd04225b7b980f75b1dab07","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2009 (2009)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2009/239892","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2009/239892","pdf_url":null,"source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W26816478","https://openalex.org/W198953946","https://openalex.org/W955355846","https://openalex.org/W1486638581","https://openalex.org/W1544527097","https://openalex.org/W1547486901","https://openalex.org/W1557133539","https://openalex.org/W1563088657","https://openalex.org/W1580938630","https://openalex.org/W1999785771","https://openalex.org/W2014915963","https://openalex.org/W2085066665","https://openalex.org/W2085457662","https://openalex.org/W2106055371","https://openalex.org/W2106339924","https://openalex.org/W2109943925","https://openalex.org/W2111339787","https://openalex.org/W2115101691","https://openalex.org/W2124864596","https://openalex.org/W2124988752","https://openalex.org/W2128838222","https://openalex.org/W2131981197","https://openalex.org/W2147292340","https://openalex.org/W2148154194","https://openalex.org/W2317919972"],"related_works":["https://openalex.org/W2348694184","https://openalex.org/W2030894524","https://openalex.org/W2592385415","https://openalex.org/W1648970942","https://openalex.org/W2802270809","https://openalex.org/W2188355725","https://openalex.org/W2143508752","https://openalex.org/W1982169401","https://openalex.org/W3197772267","https://openalex.org/W2167102385"],"abstract_inverted_index":{"We":[0],"present":[1],"an":[2],"efficient":[3],"algorithm":[4,32,186],"for":[5,51,58,89,99,198],"segmentation":[6],"of":[7,34,76,102,142,148,153,160,166],"audio":[8,22,104,193],"signals":[9,62],"into":[10],"speech":[11,59,154],"or":[12],"music.":[13],"The":[14,31],"central":[15],"motivation":[16],"to":[17,84,174,180,191],"our":[18],"study":[19],"is":[20,49,82,97,128,196],"consumer":[21],"applications,":[23],"where":[24],"various":[25,53],"real-time":[26,199],"enhancements":[27],"are":[28],"often":[29],"applied.":[30],"consists":[33],"a":[35,39,107,125,146],"learning":[36,44],"phase":[37],"and":[38,55,60,64,114,155,168,171,183,195],"classification":[40,96],"phase.":[41],"In":[42,91,178],"the":[43,66,72,77,86,92,103,123,131,143,185],"phase,":[45,94],"predefined":[46],"training":[47],"data":[48],"used":[50],"computing":[52],"time-domain":[54],"frequency-domain":[56],"features,":[57],"music":[61,161],"separately,":[63],"estimating":[65],"optimal":[67],"speech/music":[68,176],"thresholds,":[69],"based":[70],"on":[71,133,145],"probability":[73],"density":[74],"functions":[75],"features.":[78],"An":[79],"automatic":[80],"procedure":[81],"employed":[83],"select":[85],"best":[87],"features":[88],"separation.":[90],"test":[93],"initial":[95],"performed":[98],"each":[100,134],"segment":[101,135,138],"signal,":[105],"using":[106],"three-stage":[108],"sieve-like":[109],"approach,":[110],"applying":[111],"both":[112],"Bayesian":[113],"rule-based":[115],"methods.":[116],"To":[117],"avoid":[118],"erroneous":[119],"rapid":[120],"alternations":[121],"in":[122],"classification,":[124],"smoothing":[126],"technique":[127],"applied,":[129],"averaging":[130],"decision":[132],"with":[136],"past":[137],"decisions.":[139],"Extensive":[140],"evaluation":[141],"algorithm,":[144],"database":[147],"more":[149,156],"than":[150,157],"12":[151],"hours":[152,159],"22":[158],"showed":[162],"correct":[163],"identification":[164],"rates":[165],"99.4%":[167],"97.8%,":[169],"respectively,":[170],"quick":[172],"adjustment":[173],"alternating":[175],"sections.":[177],"addition":[179],"its":[181],"accuracy":[182],"robustness,":[184],"can":[187],"be":[188],"easily":[189],"adapted":[190],"different":[192],"types,":[194],"suitable":[197],"operation.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}