{"id":"https://openalex.org/W7148605845","doi":"https://doi.org/10.1109/asru65441.2025.11434790","title":"Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence","display_name":"Controllable Singing Voice Synthesis using Phoneme-Level Energy Sequence","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148605845","doi":"https://doi.org/10.1109/asru65441.2025.11434790"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5032506316","display_name":"Yerin Ryu","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Yerin Ryu","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013894332","display_name":"Inseop Shin","orcid":"https://orcid.org/0000-0001-7188-4155"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Inseop Shin","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132810421","display_name":"Chanwoo Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Korea University,Department of Artificial Intelligence,Seoul,Korea"],"affiliations":[{"raw_affiliation_string":"Korea University,Department of Artificial Intelligence,Seoul,Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032506316"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87581307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3492000102996826,"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":0.3492000102996826,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.21379999816417694,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.09290000051259995,"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":0.714900016784668},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6291000247001648},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.613099992275238},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.590499997138977},{"id":"https://openalex.org/keywords/loudness","display_name":"Loudness","score":0.5796999931335449},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5281999707221985},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.46790000796318054}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.714900016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6861000061035156},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6705999970436096},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6291000247001648},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.613099992275238},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5796999931335449},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.46790000796318054},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2948000133037567},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.2621999979019165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8518271446228027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1904711963","https://openalex.org/W3158762648","https://openalex.org/W3163031268","https://openalex.org/W3207340675","https://openalex.org/W4296069360","https://openalex.org/W4312468441","https://openalex.org/W4385571362","https://openalex.org/W4392903036","https://openalex.org/W4392904007","https://openalex.org/W4393158902","https://openalex.org/W4396214748","https://openalex.org/W4398226295","https://openalex.org/W4401042666","https://openalex.org/W4402111758","https://openalex.org/W4402112011","https://openalex.org/W4403791262","https://openalex.org/W4409348103","https://openalex.org/W4415799264"],"related_works":[],"abstract_inverted_index":{"Controllable":[0],"Singing":[1],"Voice":[2],"Synthesis":[3],"(SVS)":[4],"aims":[5],"to":[6,114],"generate":[7],"expressive":[8],"singing":[9],"voices":[10],"reflecting":[11],"user":[12],"intent.":[13],"While":[14],"recent":[15],"SVS":[16,52],"systems":[17],"achieve":[18],"high":[19],"audio":[20],"quality,":[21],"most":[22],"rely":[23],"on":[24,40,54],"probabilistic":[25],"modeling,":[26],"limiting":[27],"precise":[28],"control":[29,91],"over":[30,99],"attributes":[31],"such":[32],"as":[33],"dynamics.":[34],"We":[35,67],"address":[36],"this":[37,83],"by":[38],"focusing":[39],"dynamic":[41],"control-temporal":[42],"loudness":[43],"variation":[44],"essential":[45],"for":[46,74,110],"musical":[47],"ex-pressiveness-and":[48],"explicitly":[49],"condition":[50],"the":[51,78,85],"model":[53],"energy":[55,72,108],"sequences":[56,109],"extracted":[57],"from":[58],"ground-truth":[59],"spectrograms,":[60],"reducing":[61],"annotation":[62],"costs":[63],"and":[64,116],"improving":[65],"controllability.":[66],"also":[68],"propose":[69],"a":[70],"phoneme-level":[71,111],"sequence":[73],"user-friendly":[75],"control.":[76],"To":[77],"best":[79],"of":[80,107],"our":[81,96],"knowledge,":[82],"is":[84],"first":[86],"attempt":[87],"enabling":[88],"userdriven":[89],"dynamics":[90],"in":[92,103],"SVS.":[93],"Experiments":[94],"show":[95],"method":[97],"achieves":[98],"$50":[100],"\\%$":[101],"reduction":[102],"mean":[104],"absolute":[105],"error":[106],"inputs":[112],"compared":[113],"baseline":[115],"energy-predictor":[117],"models,":[118],"without":[119],"compromising":[120],"synthesis":[121],"quality.":[122]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}