{"id":"https://openalex.org/W2905741299","doi":"https://doi.org/10.1109/msp.2018.2875195","title":"Speech-to-Singing Voice Conversion: The Challenges and Strategies for Improving Vocal Conversion Processes","display_name":"Speech-to-Singing Voice Conversion: The Challenges and Strategies for Improving Vocal Conversion Processes","publication_year":2018,"publication_date":"2018-12-25","ids":{"openalex":"https://openalex.org/W2905741299","doi":"https://doi.org/10.1109/msp.2018.2875195","mag":"2905741299"},"language":"en","primary_location":{"id":"doi:10.1109/msp.2018.2875195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2875195","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-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"],"raw_orcid":"https://orcid.org/0000-0001-7281-1329","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":null},"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":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9158-9401","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Aichi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Aichi, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"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":1.523,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87515851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"36","issue":"1","first_page":"95","last_page":"102"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9298560619354248},{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.7653074264526367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7200015783309937},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6465072631835938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6411595344543457},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.6209942698478699},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6039272546768188},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5282889008522034},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5053915977478027},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.4254777133464813},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1958644688129425},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1162465512752533},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07806640863418579}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9298560619354248},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.7653074264526367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7200015783309937},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6465072631835938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411595344543457},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.6209942698478699},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6039272546768188},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5282889008522034},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5053915977478027},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.4254777133464813},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1958644688129425},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1162465512752533},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07806640863418579},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/msp.2018.2875195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msp.2018.2875195","pdf_url":null,"source":{"id":"https://openalex.org/S120977877","display_name":"IEEE Signal Processing Magazine","issn_l":"1053-5888","issn":["1053-5888","1558-0792"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2861704504","display_name":null,"funder_award_id":"R-263-000-C35-133/731","funder_id":"https://openalex.org/F4320320698","funder_display_name":"National University of Singapore"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W31703023","https://openalex.org/W1553896573","https://openalex.org/W1632690104","https://openalex.org/W1904711963","https://openalex.org/W1985226427","https://openalex.org/W2017857509","https://openalex.org/W2030351702","https://openalex.org/W2067709094","https://openalex.org/W2108382268","https://openalex.org/W2124097505","https://openalex.org/W2128123288","https://openalex.org/W2150769028","https://openalex.org/W2150933458","https://openalex.org/W2166472876","https://openalex.org/W2269051851","https://openalex.org/W2400703789","https://openalex.org/W2402975913","https://openalex.org/W2471520273","https://openalex.org/W2575299680","https://openalex.org/W2576309025","https://openalex.org/W2587150483","https://openalex.org/W2786387703","https://openalex.org/W2786495826","https://openalex.org/W2786868129","https://openalex.org/W2790645443","https://openalex.org/W2889064624","https://openalex.org/W2921017930","https://openalex.org/W2943968861","https://openalex.org/W3142619648","https://openalex.org/W6601272821","https://openalex.org/W6678318511","https://openalex.org/W6713343490","https://openalex.org/W6732089486","https://openalex.org/W6733275487","https://openalex.org/W6748140763","https://openalex.org/W6754413460","https://openalex.org/W6760634492","https://openalex.org/W6761425586"],"related_works":["https://openalex.org/W2378183644","https://openalex.org/W2287414930","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W3149582125","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W152045069","https://openalex.org/W652196294"],"abstract_inverted_index":{"Speech-to-singing":[0],"(STS)":[1],"conversion":[2,54],"is":[3,28,55],"the":[4,8,26,31,34,46,50],"task":[5,27,58],"of":[6,11,25,33,41],"converting":[7],"read":[9],"lyrics":[10],"a":[12,56],"song,":[13],"spoken":[14],"in":[15,65],"natural":[16,35],"manner,":[17],"to":[18,29,37],"proper":[19,42],"singing.":[20],"The":[21],"most":[22],"important":[23],"aspect":[24],"change":[30],"prosody":[32],"speech":[36],"match":[38],"with":[39],"that":[40],"singing,":[43],"while":[44],"retaining":[45],"linguistic":[47],"content":[48],"and":[49,61],"speaker's":[51],"identity.":[52],"STS":[53],"challenging":[57],"because":[59],"speaking":[60],"singing":[62],"are":[63],"different":[64],"many":[66],"ways.":[67]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}