{"id":"https://openalex.org/W2907919236","doi":"https://doi.org/10.1109/icapr.2017.8593164","title":"Vocal and Non-vocal Segmentation based on the Analysis of Formant Structure","display_name":"Vocal and Non-vocal Segmentation based on the Analysis of Formant Structure","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2907919236","doi":"https://doi.org/10.1109/icapr.2017.8593164","mag":"2907919236"},"language":"en","primary_location":{"id":"doi:10.1109/icapr.2017.8593164","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icapr.2017.8593164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","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/A5047459594","display_name":"Y. V. Srinivasa Murthy","orcid":"https://orcid.org/0000-0001-6146-5272"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Y.V. Srinivasa Murthy","raw_affiliation_strings":["NITK Surathkal, Department of CSE, Mangalore, 575 025, India"],"affiliations":[{"raw_affiliation_string":"NITK Surathkal, Department of CSE, Mangalore, 575 025, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046622313","display_name":"Shashidhar G. Koolagudi","orcid":"https://orcid.org/0000-0002-6928-0237"},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shashidhar G. Koolagudi","raw_affiliation_strings":["NITK Surathkal, Department of CSE, Mangalore, 575 025, India"],"affiliations":[{"raw_affiliation_string":"NITK Surathkal, Department of CSE, Mangalore, 575 025, India","institution_ids":["https://openalex.org/I11880225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014374206","display_name":"Vishnu G. Swaroop","orcid":null},"institutions":[{"id":"https://openalex.org/I11880225","display_name":"National Institute of Technology Karnataka","ror":"https://ror.org/01hz4v948","country_code":"IN","type":"education","lineage":["https://openalex.org/I11880225"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishnu G. Swaroop","raw_affiliation_strings":["NITK Surathkal, Department of CSE, Mangalore, 575 025, India"],"affiliations":[{"raw_affiliation_string":"NITK Surathkal, Department of CSE, Mangalore, 575 025, India","institution_ids":["https://openalex.org/I11880225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047459594"],"corresponding_institution_ids":["https://openalex.org/I11880225"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.61954047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"1","last_page":"6"},"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":0.9972000122070312,"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":0.98089998960495,"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/formant","display_name":"Formant","score":0.8925745487213135},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7428126931190491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6751989126205444},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.612820029258728},{"id":"https://openalex.org/keywords/vocal-folds","display_name":"Vocal folds","score":0.44467687606811523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3911851644515991},{"id":"https://openalex.org/keywords/larynx","display_name":"Larynx","score":0.11022570729255676},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.07493677735328674},{"id":"https://openalex.org/keywords/anatomy","display_name":"Anatomy","score":0.06316143274307251},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.05088469386100769}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8925745487213135},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7428126931190491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751989126205444},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.612820029258728},{"id":"https://openalex.org/C2780336059","wikidata":"https://www.wikidata.org/wiki/Q215558","display_name":"Vocal folds","level":3,"score":0.44467687606811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3911851644515991},{"id":"https://openalex.org/C2780474809","wikidata":"https://www.wikidata.org/wiki/Q9637","display_name":"Larynx","level":2,"score":0.11022570729255676},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.07493677735328674},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.06316143274307251},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.05088469386100769}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icapr.2017.8593164","is_oa":false,"landing_page_url":"http://doi.org/10.1109/icapr.2017.8593164","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Ninth International Conference on Advances in Pattern Recognition (ICAPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W24121424","https://openalex.org/W55723365","https://openalex.org/W169038075","https://openalex.org/W1183662111","https://openalex.org/W1607493952","https://openalex.org/W1833279920","https://openalex.org/W1945892259","https://openalex.org/W2002016471","https://openalex.org/W2015276542","https://openalex.org/W2026197045","https://openalex.org/W2048752878","https://openalex.org/W2069568528","https://openalex.org/W2107430826","https://openalex.org/W2114458328","https://openalex.org/W2124539664","https://openalex.org/W2128980425","https://openalex.org/W2138537193","https://openalex.org/W2151968358","https://openalex.org/W2154591323","https://openalex.org/W2155653793","https://openalex.org/W2164336224","https://openalex.org/W2185973722","https://openalex.org/W2212492883","https://openalex.org/W2394955069","https://openalex.org/W2406097774","https://openalex.org/W2408421357","https://openalex.org/W2548081076","https://openalex.org/W2890486777","https://openalex.org/W2890775565","https://openalex.org/W3022717317","https://openalex.org/W4242842568","https://openalex.org/W4249230140","https://openalex.org/W4285719527","https://openalex.org/W6601020138","https://openalex.org/W6602276745","https://openalex.org/W6606905016","https://openalex.org/W6680536950","https://openalex.org/W6712099778","https://openalex.org/W6713333058","https://openalex.org/W6713681473"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W37481168","https://openalex.org/W2064537740","https://openalex.org/W1980185283"],"abstract_inverted_index":{"The":[0,46,69,91],"process":[1],"of":[2,41,159],"classifying":[3],"vocal":[4,37],"and":[5,38,58,78],"non-vocal":[6,39],"regions":[7,40],"in":[8,107],"an":[9],"audio":[10],"clip":[11],"is":[12,84,161],"the":[13,36,88,100,111,146,164],"base":[14],"for":[15,34,63,75,87,134],"many":[16],"Music":[17],"Information":[18],"Retrieval":[19],"(MIR)":[20],"tasks.":[21],"In":[22],"this":[23,64],"work,":[24],"we":[25],"have":[26,60,72,96,139],"computed":[27,74,92,120],"novel":[28],"features":[29,47,95],"based":[30],"on":[31],"formant":[32,53,93,115],"structure":[33],"segmenting":[35],"a":[42,122,143,168],"given":[43],"music":[44],"clip.":[45],"such":[48],"as":[49,81,142],"obtuse":[50,70],"angles":[51,71],"at":[52],"peak,":[54],"valley":[55],"locations,":[56],"convexity,":[57],"concavity":[59],"been":[61,73,97,119,140,151],"proposed":[62,165],"task":[65],"after":[66],"thorough":[67],"analysis.":[68],"second,":[76],"third":[77],"fourth":[79],"formants":[80],"much":[82],"discrimination":[83],"not":[85],"found":[86],"first":[89],"formant.":[90],"related":[94],"added":[98],"to":[99,109,153],"base-line":[101],"Mel":[102],"frequency":[103],"cepstral":[104],"coefficients":[105],"(MFCCs)":[106],"order":[108],"improve":[110],"performance.":[112],"Moreover,":[113],"singer":[114],"(F5)":[116],"has":[117,150],"also":[118],"forming":[121],"19-dimensional":[123,169],"feature":[124,170],"vector.":[125,171],"As":[126],"artificial":[127],"neural":[128],"networks":[129],"(ANNs)":[130],"are":[131],"more":[132],"suitable":[133],"handling":[135],"nonlinear":[136],"data,":[137],"they":[138],"considered":[141],"classifier.":[144],"Further,":[145],"11-point":[147],"moving":[148],"window":[149],"applied":[152],"avoid":[154],"intermittent":[155],"misclassifications.":[156],"An":[157],"accuracy":[158],"88%":[160],"obtained":[162],"using":[163],"approach":[166],"with":[167]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}