{"id":"https://openalex.org/W2067342401","doi":"https://doi.org/10.1109/icassp.2010.5495137","title":"Parametric emotional singing voice synthesis","display_name":"Parametric emotional singing voice synthesis","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2067342401","doi":"https://doi.org/10.1109/icassp.2010.5495137","mag":"2067342401"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5013829168","display_name":"Younsung Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younsung Park","raw_affiliation_strings":["Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091430620","display_name":"Sungrack Yun","orcid":"https://orcid.org/0000-0003-2462-3854"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungrack Yun","raw_affiliation_strings":["Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073287748","display_name":"Chang D. Yoo","orcid":"https://orcid.org/0000-0002-0756-7179"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang D. Yoo","raw_affiliation_strings":["Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Department of Electrical Engineering, 2106, LG Semicon Hall, 373-1 Guseong-dong, Yuseong-gu, Daejeon 305-701, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3386,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.58500635,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4814","last_page":"4817"},"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":0.9988999962806702,"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":0.9987000226974487,"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/singing","display_name":"Singing","score":0.8798707723617554},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.7828081250190735},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7545068264007568},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7364267110824585},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.6837459802627563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.586199939250946},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5385969281196594},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5078108906745911},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5060200095176697},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5049932599067688},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4205475449562073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22367584705352783},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.21924853324890137},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21882781386375427},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10208114981651306},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09483417868614197},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08555853366851807}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8798707723617554},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.7828081250190735},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7545068264007568},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7364267110824585},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.6837459802627563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.586199939250946},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5385969281196594},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5078108906745911},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5060200095176697},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5049932599067688},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4205475449562073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22367584705352783},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.21924853324890137},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21882781386375427},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10208114981651306},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09483417868614197},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08555853366851807},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495137","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495137","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1545457992","https://openalex.org/W1866281937","https://openalex.org/W1984677178","https://openalex.org/W1989104072","https://openalex.org/W2045170765","https://openalex.org/W2077466407","https://openalex.org/W2106792148","https://openalex.org/W2129142580","https://openalex.org/W2145892079","https://openalex.org/W2148600927","https://openalex.org/W2149628368","https://openalex.org/W2150791533","https://openalex.org/W2154920538","https://openalex.org/W2170794519","https://openalex.org/W2339343773","https://openalex.org/W2938558181","https://openalex.org/W3142087749","https://openalex.org/W4230277160"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W4230480656","https://openalex.org/W2978145617","https://openalex.org/W2108382268","https://openalex.org/W2097873655","https://openalex.org/W2023774214"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"algorithm":[4,138],"to":[5,37,59,78,119,128],"control":[6,140],"the":[7,16,50,60,64,75,79,88,95,101,112,115,120,130,137,141],"expressed":[8,142],"emotion":[9,143],"of":[10,18,26,32,100,104,144],"a":[11,105,145,149],"synthesized":[12,86,106,131],"song.":[13,132],"Based":[14],"on":[15],"database":[17],"various":[19],"melodies":[20],"sung":[21],"neutrally":[22],"with":[23,74],"restricted":[24],"set":[25,77],"words,":[27],"hidden":[28],"semi-Markov":[29],"models":[30],"(HSMMs)":[31],"notes":[33,61],"ranging":[34],"from":[35,71],"E3":[36],"G5":[38],"are":[39,47,56,69],"constructed":[40],"for":[41],"synthesizing":[42],"singing":[43,146,151],"voice.":[44],"Three":[45],"steps":[46],"taken":[48],"in":[49],"synthesis:":[51],"(1)":[52],"Pitch":[53],"and":[54,114],"duration":[55,76,113],"determined":[57],"according":[58,118],"indicated":[62],"by":[63,87,110],"musical":[65],"score;":[66],"(2)":[67],"Features":[68],"sampled":[70,96],"appropriate":[72],"HSMMs":[73],"maximum":[80],"probability;":[81],"(3)":[82],"Singing":[83],"voice":[84,147,152],"is":[85,108,126],"mel-log":[89],"spectrum":[90],"approximation":[91],"(MLSA)":[92],"filter":[93],"using":[94],"features":[97],"as":[98],"parameters":[99,117],"filter.":[102],"Emotion":[103],"song":[107],"controlled":[109],"varying":[111],"vibrato":[116],"Thayer's":[121],"mood":[122],"model.":[123],"Perception":[124],"test":[125],"performed":[127],"evaluate":[129],"The":[133],"results":[134],"show":[135],"that":[136],"can":[139],"given":[148],"neutral":[150],"database.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}