{"id":"https://openalex.org/W2790746963","doi":"https://doi.org/10.1109/vcip.2017.8305078","title":"Assessment and classification of singing quality based on audio-visual features","display_name":"Assessment and classification of singing quality based on audio-visual features","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2790746963","doi":"https://doi.org/10.1109/vcip.2017.8305078","mag":"2790746963"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2017.8305078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","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/A5054309616","display_name":"Mangona Bokshi","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mangona Bokshi","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101452102","display_name":"Fei Tao","orcid":"https://orcid.org/0000-0003-4834-8949"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Tao","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.21969697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.939548134803772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7215307354927063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6558874845504761},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6354740858078003},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5101433396339417},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.45442911982536316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3806915283203125},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.19067031145095825},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10733035206794739}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.939548134803772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7215307354927063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6558874845504761},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6354740858078003},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5101433396339417},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.45442911982536316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3806915283203125},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.19067031145095825},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10733035206794739},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip.2017.8305078","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2017.8305078","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Visual Communications and Image Processing (VCIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W109946471","https://openalex.org/W1973249776","https://openalex.org/W2002125932","https://openalex.org/W2047387911","https://openalex.org/W2053089284","https://openalex.org/W2074654860","https://openalex.org/W2078895845","https://openalex.org/W2080014633","https://openalex.org/W2111030185","https://openalex.org/W2133990480","https://openalex.org/W2138997758","https://openalex.org/W2157285372","https://openalex.org/W2170416904","https://openalex.org/W2186775857","https://openalex.org/W2267146270","https://openalex.org/W2408133286","https://openalex.org/W3029238381","https://openalex.org/W6604464690","https://openalex.org/W6714284516"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W153239700","https://openalex.org/W2067459736","https://openalex.org/W2105635394"],"abstract_inverted_index":{"The":[0,146,183],"process":[1],"of":[2,38,46,50,61,77,92,127],"speech":[3,104],"production":[4],"changes":[5],"between":[6,74],"speaking":[7],"and":[8,17,58,107,120,124,131,160,171,191],"singing":[9,48,90,98,103,187],"due":[10,42],"to":[11,43,67,185],"excitation,":[12],"vocal":[13],"tract":[14],"articulatory":[15],"positioning,":[16],"cognitive":[18],"motor":[19],"planning":[20],"while":[21,179],"singing.":[22,39,78],"Singing":[23],"does":[24],"not":[25],"only":[26],"deviate":[27],"from":[28,94,189],"typical":[29],"spoken":[30],"speech,":[31],"but":[32],"it":[33,64],"varies":[34],"across":[35],"various":[36],"styles":[37],"This":[40],"is":[41,65,168,197],"alternative":[44],"genres":[45],"music,":[47],"quality":[49,91,177,188],"an":[51,95,175],"individual,":[52],"as":[53,55],"well":[54],"different":[56,140],"languages":[57],"cultures.":[59],"Because":[60],"this":[62,80,195],"variation,":[63],"important":[66],"establish":[68,83],"a":[69,84],"baseline":[70],"system":[71,86],"for":[72],"differentiating":[73],"certain":[75],"aspects":[76],"In":[79],"study,":[81],"we":[82],"classification":[85],"that":[87,114,149,169],"automatically":[88],"estimates":[89],"candidates":[93],"American":[96],"TV":[97],"show":[99,148],"based":[100,138],"on":[101,139],"their":[102],"acoustics,":[105],"lip":[106,159,170,190],"eye":[108,144,161,172,192],"movements.":[109],"We":[110,134],"employ":[111],"three":[112],"classifiers":[113],"include:":[115],"Logistic":[116],"Regression,":[117],"Naive":[118],"Bayes":[119],"K-nearest":[121],"neighbor":[122],"(k-NN)":[123],"compare":[125,136],"performance":[126,137],"each":[128],"using":[129],"unimodal":[130],"multimodal":[132],"features.":[133],"also":[135],"modalities":[141],"(speech,":[142],"lip,":[143],"structure).":[145],"results":[147],"audio":[150,180],"content":[151,162,173,193],"performs":[152],"the":[153],"best,":[154],"with":[155],"modest":[156],"gains":[157],"when":[158],"are":[163],"fused.":[164],"An":[165],"interesting":[166],"outcome":[167],"achieve":[174],"82%":[176],"assessment":[178],"achieves":[181],"95%.":[182],"ability":[184],"assess":[186],"at":[194],"level":[196],"remarkable.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}