{"id":"https://openalex.org/W2401296648","doi":"https://doi.org/10.21437/interspeech.2015-580","title":"Statistical singing voice conversion based on direct waveform modification with global variance","display_name":"Statistical singing voice conversion based on direct waveform modification with global variance","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2401296648","doi":"https://doi.org/10.21437/interspeech.2015-580","mag":"2401296648"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000692949","display_name":"Graham Neubig","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037417355"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2975,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.89657183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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":0.9994999766349792,"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":0.996399998664856,"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/waveform","display_name":"Waveform","score":0.7465491890907288},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6538134217262268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5652251243591309},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5529298782348633},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5162372589111328},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.29627594351768494},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1740666627883911},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07334372401237488},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06715202331542969}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7465491890907288},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6538134217262268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5652251243591309},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5529298782348633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5162372589111328},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29627594351768494},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1740666627883911},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07334372401237488},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06715202331542969},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-580","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W111300696","https://openalex.org/W1482298176","https://openalex.org/W1590808459","https://openalex.org/W1596263485","https://openalex.org/W1999405202","https://openalex.org/W2049686551","https://openalex.org/W2060554399","https://openalex.org/W2097873655","https://openalex.org/W2111037747","https://openalex.org/W2120605154","https://openalex.org/W2145892079","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2294038178","https://openalex.org/W2408435475","https://openalex.org/W2763280966"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390529913","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W1969227305","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"techniques":[3,130],"to":[4,31,61,69,90,113,149],"improve":[5,132],"the":[6,54,74,77,92,96,102,105,128,136,142,150],"quality":[7,52,134],"of":[8,36,42,53,63,76,95,104,121,135,145],"voices":[9],"generated":[10],"through":[11],"statistical":[12],"singing":[13,33,56,66,138],"voice":[14,34,57,67,139],"conversion":[15,143],"with":[16],"direct":[17],"waveform":[18,49],"modification":[19],"based":[20],"on":[21],"spectrum":[22],"differential":[23],"(DIFFSVC).":[24],"The":[25],"DIFFSVC":[26,106],"method":[27],"makes":[28],"it":[29],"possible":[30],"convert":[32],"characteristics":[35],"a":[37,43,64,88],"source":[38],"singer":[39,45,146],"into":[40],"those":[41],"target":[44],"without":[46],"using":[47],"vocoder-based":[48],"generation.":[50],"However,":[51],"converted":[55,78,97,137],"still":[58],"degrades":[59],"compared":[60,148],"that":[62,127],"natural":[65],"due":[68],"various":[70],"factors,":[71],"such":[72],"as":[73],"over-smoothing":[75,116],"spectral":[79,98],"parameter":[80,99],"trajectory.":[81],"To":[82],"alleviate":[83],"this":[84],"over-smoothing,":[85],"we":[86],"propose":[87,110],"technique":[89,112],"restore":[91],"global":[93],"variance":[94],"trajectory":[100],"within":[101],"framework":[103],"method.":[107],"We":[108],"also":[109],"another":[111],"specifically":[114],"avoid":[115],"at":[117],"unvoiced":[118],"frames.":[119],"Results":[120],"subjective":[122],"and":[123],"objective":[124],"evaluations":[125],"demonstrate":[126],"proposed":[129],"significantly":[131],"speech":[133],"while":[140],"preserving":[141],"accuracy":[144],"identity":[147],"conventional":[151],"DIFFSVC.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}