{"id":"https://openalex.org/W3010943931","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023056","title":"Speaker-independent Spectral Mapping for Speech-to-Singing Conversion","display_name":"Speaker-independent Spectral Mapping for Speech-to-Singing Conversion","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010943931","doi":"https://doi.org/10.1109/apsipaasc47483.2019.9023056","mag":"3010943931"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc47483.2019.9023056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 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/A5101856962","display_name":"Xiaoxue Gao","orcid":"https://orcid.org/0000-0003-1920-5228"},"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":"Xiaoxue Gao","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/A5103156833","display_name":"Xiaohai Tian","orcid":"https://orcid.org/0000-0001-5219-1249"},"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":"Xiaohai Tian","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/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"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":"Rohan Kumar Das","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/A5101846956","display_name":"Yi Zhou","orcid":"https://orcid.org/0000-0002-8520-8227"},"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":"Yi Zhou","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":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"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, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101856962"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.4002,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86814515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"164"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9304599761962891},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7877193689346313},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7487289309501648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7085326910018921},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44920364022254944},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4465376138687134},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4228115975856781},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3613753318786621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3096044063568115},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17933228611946106}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9304599761962891},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7877193689346313},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7487289309501648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7085326910018921},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44920364022254944},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4465376138687134},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4228115975856781},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3613753318786621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3096044063568115},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17933228611946106},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/apsipaasc47483.2019.9023056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc47483.2019.9023056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W31703023","https://openalex.org/W1492383498","https://openalex.org/W1497120562","https://openalex.org/W1535240601","https://openalex.org/W1553896573","https://openalex.org/W1602430027","https://openalex.org/W1607893546","https://openalex.org/W2030040952","https://openalex.org/W2064005251","https://openalex.org/W2067709094","https://openalex.org/W2107860279","https://openalex.org/W2108382268","https://openalex.org/W2117418893","https://openalex.org/W2121387787","https://openalex.org/W2128123288","https://openalex.org/W2128160875","https://openalex.org/W2150769028","https://openalex.org/W2150933458","https://openalex.org/W2154920538","https://openalex.org/W2165108269","https://openalex.org/W2400703789","https://openalex.org/W2402975913","https://openalex.org/W2404620314","https://openalex.org/W2405464168","https://openalex.org/W2407667681","https://openalex.org/W2471520273","https://openalex.org/W2574092538","https://openalex.org/W2598638573","https://openalex.org/W2785608393","https://openalex.org/W2785978752","https://openalex.org/W2786495826","https://openalex.org/W2806000759","https://openalex.org/W2889064624","https://openalex.org/W2892734764","https://openalex.org/W2898832121","https://openalex.org/W2911340057","https://openalex.org/W2921017930","https://openalex.org/W2938583109","https://openalex.org/W2943968861","https://openalex.org/W4211139177","https://openalex.org/W6601272821","https://openalex.org/W6631966783","https://openalex.org/W6636404455","https://openalex.org/W6713043798","https://openalex.org/W6713343490","https://openalex.org/W6713491369","https://openalex.org/W6714125293","https://openalex.org/W6752162899","https://openalex.org/W6758191806"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speech-to-Singing":[0],"(STS)":[1],"conversion":[2],"aims":[3],"at":[4],"converting":[5],"one's":[6],"reading":[7],"speech":[8,24,36,117],"into":[9],"his/her":[10],"singing":[11,88,119],"vocal.":[12],"The":[13,76,86,125,139],"prior":[14],"work":[15],"was":[16],"mainly":[17],"focused":[18],"on":[19,69,143],"transforming":[20],"the":[21,33,99,104,114,150,155],"prosody":[22,95],"of":[23,35,54,106,159],"to":[25,41,51,59,71,97,112],"singing,":[26,38],"however,":[27],"there":[28],"exist":[29],"prominent":[30],"differences":[31,115],"between":[32,116],"spectra":[34,89,120],"and":[37,118,145,161],"which":[39,66],"need":[40],"be":[42],"transformed":[43],"as":[44],"well.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"make":[52],"use":[53],"parallel":[55,131],"multi-speaker":[56],"speak-sing":[57,132],"data":[58,133],"develop":[60],"a":[61,122],"speaker-independent":[62],"spectral":[63,83],"mapping":[64,84],"model,":[65],"is":[67,78],"conditioned":[68,82],"i-vector":[70,107],"generate":[72],"target":[73,100,135],"speaker/singer":[74],"identity.":[75],"model":[77,110,113,127],"therefore":[79],"called":[80],"speaker":[81],"model.":[85],"converted":[87],"are":[90],"then":[91],"used":[92],"together":[93],"with":[94],"features":[96],"synthesize":[98],"singing.":[101],"We":[102],"investigate":[103],"effectiveness":[105],"based":[108],"average":[109],"adaptation":[111],"for":[121],"specific":[123],"speaker.":[124],"proposed":[126,151],"does":[128],"not":[129],"require":[130],"from":[134],"speakers":[136],"during":[137],"training.":[138],"experimental":[140],"results":[141],"conducted":[142],"NUS-48E":[144],"NUS-HLT-SLS":[146],"database":[147],"indicate":[148],"that":[149],"approach":[152],"significantly":[153],"outperforms":[154],"baselines":[156],"in":[157],"terms":[158],"quality":[160],"similarity.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}