{"id":"https://openalex.org/W2988096809","doi":"https://doi.org/10.1121/1.5137261","title":"Analysis and modeling for modification of speaking to karaoke-style singing","display_name":"Analysis and modeling for modification of speaking to karaoke-style singing","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2988096809","doi":"https://doi.org/10.1121/1.5137261","mag":"2988096809"},"language":"en","primary_location":{"id":"doi:10.1121/1.5137261","doi":"https://doi.org/10.1121/1.5137261","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137261","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/A5025206583","display_name":"Soheil Khorram","orcid":"https://orcid.org/0000-0002-2306-3341","observed_orcids":["https://orcid.org/0000-0002-2306-3341"]},"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":true,"raw_author_name":"Soheil Khorram","raw_affiliation_strings":["Univ. of Texas at Dallas, 2400 Waterview Pkwy, Apt. 436, Richardson, TX 75080, khorram.soheil@gmail.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Dallas, 2400 Waterview Pkwy, Apt. 436, Richardson, TX 75080, khorram.soheil@gmail.com","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","observed_orcids":["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. Hansen","raw_affiliation_strings":["Univ. of Texas at Dallas, Richardson, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Texas at Dallas, Richardson, TX","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5025206583"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"146","issue":"4_Supplement","first_page":"2955","last_page":"2955"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9082000255584717,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9082000255584717,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.06469999998807907,"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":0.020899999886751175,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-modification","display_name":"voice modification","score":0.9509999752044678},{"id":"https://openalex.org/keywords/prosody","display_name":"prosody","score":0.5580000281333923},{"id":"https://openalex.org/keywords/spectral-properties","display_name":"spectral properties","score":0.8579999804496765},{"id":"https://openalex.org/keywords/resnet","display_name":"ResNet","score":0.8240000009536743},{"id":"https://openalex.org/keywords/subjective-evaluation","display_name":"subjective evaluation","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8799012899398804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733231246471405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6272249817848206},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5677413940429688},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5529320240020752},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4642171859741211},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4402993321418762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30408570170402527},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2190166413784027},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14217814803123474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11614137887954712},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11315920948982239},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.09348052740097046},{"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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.5137261","doi":"https://doi.org/10.1121/1.5137261","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.5137261","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3056518849","https://openalex.org/W7006552968","https://openalex.org/W2150933458","https://openalex.org/W2606502962","https://openalex.org/W7100368785","https://openalex.org/W7095922737","https://openalex.org/W4297841449","https://openalex.org/W2128123288","https://openalex.org/W2375367034","https://openalex.org/W4408345783"],"abstract_inverted_index":{"This":[0,91],"study":[1],"considers":[2],"an":[3],"analysis":[4],"of":[5,13,48,116,147,190],"differences":[6],"in":[7,22,26],"voice":[8,101],"modification":[9,102,141],"within":[10],"the":[11,17,23,68,84,121,128,144,148,156,161,165,176,179,188,191],"domains":[12],"speaking":[14,28,120,137],"and":[15,60,75,113],"singing":[16,77,118,140],"same":[18,69,122],"text":[19,70,123],"content,":[20],"resulting":[21],"first":[24,73,105],"attempt":[25],"converting":[27],"to":[29,66,83,109,134,138,174,186],"Karaoke-Style":[30,139],"singing.":[31],"To":[32],"develop":[33,135],"this":[34,107,132],"system,":[35,150],"we":[36,151,159,169],"collected":[37],"a":[38,94,136,171],"new":[39],"dataset,":[40,42],"UT-Sing":[41],"containing":[43],"more":[44],"than":[45],"23":[46],"h":[47],"speech":[49],"from":[50,131],"81":[51],"participants":[52],"across":[53],"four":[54],"different":[55,111],"languages:":[56],"English,":[57],"Farsi,":[58],"Hindi,":[59],"Mandarin.":[61],"We":[62,104,125,182],"asked":[63],"each":[64],"participant":[65],"produce":[67],"content":[71],"by":[72],"reading":[74],"then":[76,126],"5":[78],"popular":[79],"songs":[80],"while":[81],"listening":[82],"accompanying":[85],"instrumental":[86],"music":[87],"through":[88,164],"open-air":[89],"headphones.":[90],"effectively":[92],"creates":[93],"parallel":[95],"dataset":[96,108],"that":[97],"is":[98],"suitable":[99],"for":[100],"systems.":[103],"use":[106],"compare":[110],"prosodic":[112],"spectral":[114],"characteristics":[115],"Karaoke-style":[117],"versus":[119],"content.":[124],"leverage":[127],"knowledge":[129],"obtained":[130],"comparison":[133],"system.":[142,193],"In":[143],"training":[145],"phase":[146],"developed":[149,192],"extract":[152],"acoustic":[153,162,180],"features":[154,163],"using":[155],"WORLD":[157],"vocoder;":[158],"align":[160],"DTW":[166],"algorithm.":[167],"Finally,":[168],"train":[170],"residual":[172],"network":[173],"model":[175],"relationship":[177],"between":[178],"features.":[181],"employ":[183],"subjective":[184],"assessments":[185],"evaluate":[187],"performance":[189]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-11-22T00:00:00"}