{"id":"https://openalex.org/W2786495826","doi":"https://doi.org/10.1109/apsipa.2017.8282289","title":"A dual alignment scheme for improved speech-to-singing voice conversion","display_name":"A dual alignment scheme for improved speech-to-singing voice conversion","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786495826","doi":"https://doi.org/10.1109/apsipa.2017.8282289","mag":"2786495826"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5016027101","display_name":"Karthika Vijayan","orcid":"https://orcid.org/0000-0001-7281-1329"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Karthika Vijayan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Human Language Technology Department, Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","Human Language Technology Department, Institute for Infocomm Research, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Human Language Technology Department, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016027101"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.3402,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.91457076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"1547","last_page":"1555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8834913969039917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8317362070083618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569389343261719},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.6936930418014526},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5093844532966614},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.42261308431625366},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3248705565929413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3077244162559509},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2054547667503357},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11771467328071594}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8834913969039917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8317362070083618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569389343261719},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.6936930418014526},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5093844532966614},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.42261308431625366},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3248705565929413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3077244162559509},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2054547667503357},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11771467328071594},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W31703023","https://openalex.org/W40007022","https://openalex.org/W49522132","https://openalex.org/W170732776","https://openalex.org/W188353524","https://openalex.org/W1575182257","https://openalex.org/W1590808459","https://openalex.org/W1995078524","https://openalex.org/W2017857509","https://openalex.org/W2028272688","https://openalex.org/W2049686551","https://openalex.org/W2066598518","https://openalex.org/W2083162014","https://openalex.org/W2088867696","https://openalex.org/W2089170860","https://openalex.org/W2096545254","https://openalex.org/W2096801154","https://openalex.org/W2102870814","https://openalex.org/W2108382268","https://openalex.org/W2116456725","https://openalex.org/W2124097505","https://openalex.org/W2128123288","https://openalex.org/W2128160875","https://openalex.org/W2150933458","https://openalex.org/W2152591660","https://openalex.org/W2154679358","https://openalex.org/W2164282073","https://openalex.org/W2168987487","https://openalex.org/W2269051851","https://openalex.org/W2294038178","https://openalex.org/W2318584973","https://openalex.org/W2396693183","https://openalex.org/W2400703789","https://openalex.org/W2401296648","https://openalex.org/W2407667681","https://openalex.org/W2482558056","https://openalex.org/W2586453598","https://openalex.org/W3142619648","https://openalex.org/W6601272821","https://openalex.org/W6607540946","https://openalex.org/W6678318511","https://openalex.org/W6682478880","https://openalex.org/W6697024540","https://openalex.org/W6712312341","https://openalex.org/W6712902469","https://openalex.org/W6713043798"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2341338763","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2950183183","https://openalex.org/W2030799363","https://openalex.org/W2340348677","https://openalex.org/W2130799169","https://openalex.org/W127416991"],"abstract_inverted_index":{"In":[0,62],"speech-to-singing":[1],"(STS)":[2],"voice":[3],"conversion,":[4],"the":[5,32,48,98,123,129,135,148,168,195,201,206],"source":[6,92,130],"speech":[7,33,43,71,93,96,112,131],"signals":[8,44],"from":[9],"a":[10,20,158,178],"speaker":[11],"are":[12],"used":[13],"to":[14,47,90,94],"generate":[15],"his/her":[16],"singing":[17,53,73,115,124,143,189],"voice.":[18],"Such":[19],"process":[21],"requires":[22],"accurate":[23,108],"detection":[24],"of":[25,39,42,59,101,122,151,161,181,187],"boundaries":[26],"between":[27,110],"phonemes":[28],"and":[29,37,72,113],"words":[30],"in":[31,75,97,163,183,191,210],"signal.":[34],"The":[35,82,154],"computation":[36],"modification":[38],"analysis":[40],"parameters":[41],"with":[45,134,142,205],"respect":[46],"target":[49,114],"musical":[50],"scores":[51,186],"or":[52],"templates,":[54],"largely":[55],"depend":[56],"upon":[57],"estimation":[58],"phoneme":[60],"durations.":[61],"this":[63],"paper,":[64],"an":[65,107],"improved":[66],"dual":[67,102,152,203],"alignment":[68,165,204],"scheme":[69,156],"for":[70],"voices":[74,190],"template-based":[76],"STS":[77,211],"(TSTS)":[78],"systems":[79],"is":[80,88,132,139,208],"proposed.":[81],"subsequence":[83],"dynamic":[84,170],"time":[85,171],"warping":[86,172],"(subDTW)":[87],"employed":[89],"match":[91],"singer's":[95,111,136],"first":[99],"pass":[100,150],"alignment.":[103,153],"We":[104,198],"assume":[105],"that":[106,145,200],"correspondence":[109],"vocals":[116],"has":[117],"been":[118],"established":[119],"as":[120],"part":[121],"template":[125],"development.":[126],"Therefore,":[127],"once":[128],"aligned":[133,141],"speech,":[137],"it":[138,176],"automatically":[140],"template,":[144],"we":[146],"call":[147],"second":[149],"proposed":[155,202],"delivers":[157],"relative":[159,179],"reduction":[160],"95.8%":[162],"word":[164],"error,":[166],"over":[167,194],"baseline":[169],"(DTW)":[173],"approach.":[174],"Also,":[175],"provides":[177],"improvement":[180],"38.7%":[182],"mean":[184],"opinion":[185],"synthesized":[188],"subjective":[192],"studies,":[193],"same":[196],"baseline.":[197],"demonstrate":[199],"subDTW":[207],"effective":[209],"conversion":[212],"applications.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}