{"id":"https://openalex.org/W4405709821","doi":"https://doi.org/10.1109/iscslp63861.2024.10800412","title":"ExpressiveSinger: Synthesizing Expressive Singing Voice as an Instrument","display_name":"ExpressiveSinger: Synthesizing Expressive Singing Voice as an Instrument","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709821","doi":"https://doi.org/10.1109/iscslp63861.2024.10800412"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101419335","display_name":"Fengping Wang","orcid":"https://orcid.org/0009-0001-4420-4553"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fengping Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099111159","display_name":"Bingsong Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingsong Bai","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008597430","display_name":"Yayue Deng","orcid":"https://orcid.org/0009-0003-7642-4942"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yayue Deng","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033565985","display_name":"Jinlong Xue","orcid":"https://orcid.org/0009-0000-0442-0932"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong Xue","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033063238","display_name":"Yingming Gao","orcid":"https://orcid.org/0000-0001-5881-3723"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingming Gao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101419335"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24598291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"304","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9031000137329102,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9031000137329102,"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":0.835024893283844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6417250037193298},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4834052622318268},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36168354749679565},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.25789207220077515}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.835024893283844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6417250037193298},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4834052622318268},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36168354749679565},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25789207220077515},{"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/iscslp63861.2024.10800412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2249315591","display_name":null,"funder_award_id":"62271083","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4956350551","display_name":null,"funder_award_id":"2023RC73,2023RC13","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W111300696","https://openalex.org/W1904711963","https://openalex.org/W2111037747","https://openalex.org/W2963609956","https://openalex.org/W3097514409","https://openalex.org/W3207340675","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4221167708","https://openalex.org/W4226332109","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4372190416","https://openalex.org/W4384028538","https://openalex.org/W4385823416","https://openalex.org/W6674766369","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6810689344"],"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":{"In":[0],"this":[1],"study,":[2],"we":[3,57,77],"introduce":[4],"ExpressiveSinger,":[5],"an":[6],"end-to-end":[7,84],"ex-pressive":[8],"singing":[9,74,99,123],"voices":[10],"synthesis":[11],"model,":[12],"which":[13],"accurately":[14],"re-flect":[15],"users'":[16],"musical":[17],"expression":[18],"by":[19],"analyzing":[20],"real-played":[21,53],"MIDI":[22,37,54,127],"sequences":[23,38,44],"and":[24,62,69,106,116,125],"lyrics.":[25],"We":[26],"propose":[27],"a":[28,79,117],"novel":[29],"method":[30,105],"to":[31,52,66,86],"auto-matically":[32],"annotate":[33],"velocity":[34,49],"labels":[35],"for":[36,83],"in":[39,112],"SVS":[40],"datasets,":[41],"as":[42],"these":[43],"do":[45],"not":[46],"inherently":[47],"contain":[48],"information":[50],"compared":[51],"sequences.":[55],"More-over,":[56],"separately":[58],"model":[59],"expressive":[60],"features":[61],"modify":[63],"the":[64,72,96,108,121,126],"vocoder":[65],"enhance":[67],"controllability":[68],"quality":[70],"of":[71,110,114],"synthetic":[73,122],"voices.":[75],"Finally,":[76],"adopt":[78],"soft-vc":[80],"like":[81],"approach":[82],"training":[85],"effectively":[87],"preserve":[88],"more":[89],"linguistic":[90],"content":[91],"features.":[92],"Our":[93],"experiments":[94],"on":[95],"professional":[97],"Mandarin":[98],"corpus":[100],"validate":[101],"our":[102],"data":[103],"annotation":[104],"demonstrate":[107],"effectiveness":[109],"ExpressiveSinger":[111],"terms":[113],"naturalness":[115],"strong":[118],"correlation":[119],"between":[120],"voice":[124],"input.":[128]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
