{"id":"https://openalex.org/W4396214748","doi":"https://doi.org/10.1109/taslp.2024.3394769","title":"SinTechSVS: A Singing Technique Controllable Singing Voice Synthesis System","display_name":"SinTechSVS: A Singing Technique Controllable Singing Voice Synthesis System","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396214748","doi":"https://doi.org/10.1109/taslp.2024.3394769"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3394769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3394769","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5104290513","display_name":"Junchuan Zhao","orcid":"https://orcid.org/0009-0008-2616-6590"},"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":"Junchuan Zhao","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0008-2616-6590","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095926434","display_name":"Low Qi Hong Chetwin","orcid":"https://orcid.org/0009-0004-2367-5171"},"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":"Low Qi Hong Chetwin","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-2367-5171","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"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":"Ye Wang","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0123-1260","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":2.0963,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8746822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2641","last_page":"2653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9692109823226929},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42402809858322144},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4163474440574646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3877990245819092},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.37157392501831055},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2053930163383484},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08345729112625122}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9692109823226929},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42402809858322144},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4163474440574646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3877990245819092},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.37157392501831055},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2053930163383484},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08345729112625122}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3394769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3394769","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7835538620","display_name":null,"funder_award_id":"MOE-T2EP20120-0012","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W241723195","https://openalex.org/W1904711963","https://openalex.org/W1979451170","https://openalex.org/W1995078524","https://openalex.org/W2049367655","https://openalex.org/W2102870814","https://openalex.org/W2109255472","https://openalex.org/W2111037747","https://openalex.org/W2120605154","https://openalex.org/W2136507169","https://openalex.org/W2142603079","https://openalex.org/W2153748620","https://openalex.org/W2188454546","https://openalex.org/W2194775991","https://openalex.org/W2515336442","https://openalex.org/W2725868244","https://openalex.org/W2763782214","https://openalex.org/W2777781175","https://openalex.org/W2778460379","https://openalex.org/W2787247660","https://openalex.org/W2887280559","https://openalex.org/W2963267809","https://openalex.org/W3016250102","https://openalex.org/W3027728407","https://openalex.org/W3081279708","https://openalex.org/W3082910224","https://openalex.org/W3095074555","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W3204116061","https://openalex.org/W4200473284","https://openalex.org/W4210682690","https://openalex.org/W4210777104","https://openalex.org/W4221167708","https://openalex.org/W4225919501","https://openalex.org/W4283652003","https://openalex.org/W4290647479","https://openalex.org/W4296068763","https://openalex.org/W4312468441","https://openalex.org/W4382912912","https://openalex.org/W4384028538","https://openalex.org/W6623517193","https://openalex.org/W6678318511","https://openalex.org/W6687226521","https://openalex.org/W6711617558","https://openalex.org/W6713438261","https://openalex.org/W6713876852","https://openalex.org/W6731370813","https://openalex.org/W6739412746","https://openalex.org/W6740333300","https://openalex.org/W6746974885","https://openalex.org/W6757202746","https://openalex.org/W6771811022","https://openalex.org/W6783382068","https://openalex.org/W6810689344","https://openalex.org/W6838416371","https://openalex.org/W6846351131","https://openalex.org/W6846452521","https://openalex.org/W7033935004"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795"],"abstract_inverted_index":{"The":[0],"precise":[1],"control":[2,41,149],"of":[3,7,58,118,134,163,172],"singing":[4,43,52,60,64,70,80,95,103,111,151,174],"techniques":[5],"is":[6,167],"utmost":[8],"importance":[9],"in":[10],"achieving":[11],"emotionally":[12],"expressive":[13],"vocal":[14,136],"performances.":[15],"To":[16,160],"bridge":[17],"the":[18,85,115,130,161,168],"gap":[19],"between":[20],"current":[21],"Singing":[22,119],"Voice":[23],"Synthesis":[24],"(SVS)":[25],"systems":[26,146],"and":[27,68,83,92,132,147,157],"human":[28],"singers,":[29],"our":[30,164],"paper":[31],"focuses":[32],"on":[33],"developing":[34],"an":[35,93],"SVS":[36,55,145,170],"system":[37,56],"that":[38,126],"allows":[39],"for":[40,78,114],"over":[42,150],"techniques.":[44,175],"In":[45],"this":[46],"paper,":[47],"we":[48],"introduce":[49],"SinTechSVS,":[50],"a":[51,59,63,69,109],"technique":[53,61,65,71,81,96,104,112],"controllable":[54,66],"composed":[57],"annotator,":[62],"synthesizer,":[67],"recommender.":[72],"Our":[73],"approach":[74],"leverages":[75],"transfer":[76],"learning":[77],"efficient":[79],"annotation":[82],"adapts":[84],"DiffSinger":[86],"framework":[87],"with":[88,138],"additional":[89],"style":[90],"encoders":[91],"attention-based":[94],"local":[97],"score":[98],"(STLS)":[99],"module":[100],"to":[101,143],"enhance":[102],"controllability.":[105],"We":[106],"also":[107],"propose":[108],"Seq2Seq":[110],"recommender":[113],"new":[116],"task":[117],"Technique":[120],"Recommendation":[121],"(STR).":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"SinTechSVS":[127,166],"significantly":[128],"improves":[129],"quality":[131],"expressiveness":[133],"synthesized":[135],"performances,":[137],"comparable":[139],"general":[140],"synthesis":[141],"capabilities":[142],"state-of-the-art":[144],"enhanced":[148],"techniques,":[152],"as":[153],"evidenced":[154],"by":[155],"objective":[156],"subjective":[158],"evaluations.":[159],"best":[162],"knowledge,":[165],"first":[169],"capable":[171],"controlling":[173]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}