{"id":"https://openalex.org/W2294038178","doi":"https://doi.org/10.21437/interspeech.2014-539","title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","display_name":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2294038178","doi":"https://doi.org/10.21437/interspeech.2014-539","mag":"2294038178"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-539","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science & Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science & Technology#TAB#","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037417355"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8838,"has_fulltext":false,"cited_by_count":87,"citation_normalized_percentile":{"value":0.96286197,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"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/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"}},"topics":[{"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9879999756813049,"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":0.776921272277832},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7086796164512634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5835663080215454},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5340712666511536},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.45748865604400635},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42905017733573914},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.15967229008674622},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12209036946296692}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.776921272277832},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7086796164512634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5835663080215454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5340712666511536},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.45748865604400635},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42905017733573914},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.15967229008674622},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12209036946296692},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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.2014-539","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W111300696","https://openalex.org/W1482298176","https://openalex.org/W1590808459","https://openalex.org/W1596263485","https://openalex.org/W2007023536","https://openalex.org/W2049686551","https://openalex.org/W2097873655","https://openalex.org/W2110589840","https://openalex.org/W2111037747","https://openalex.org/W2120605154","https://openalex.org/W2130081501","https://openalex.org/W2145892079","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2395578248","https://openalex.org/W2408435475","https://openalex.org/W2763280966"],"related_works":["https://openalex.org/W3207249698","https://openalex.org/W1528909574","https://openalex.org/W2122830402","https://openalex.org/W2552590214","https://openalex.org/W2034702404","https://openalex.org/W3207038517","https://openalex.org/W2921857201","https://openalex.org/W169038075","https://openalex.org/W2329661839","https://openalex.org/W2951961943"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,26,32,37,81,105,141,157],"novel":[4],"statistical":[5,106,202],"singing":[6,42,51,72,83,131,183,200],"voice":[7,23,43,52,73,84,184,203],"conversion":[8,107,158,188],"(SVC)":[9],"technique":[10],"with":[11],"direct":[12],"waveform":[13,116],"modification":[14],"based":[15],"on":[16],"the":[17,70,96,112,115,120,123,126,152,161,169,181,187,195],"spectrum":[18],"differential":[19,134,142,209],"that":[20,30,79,109,147,168],"can":[21],"convert":[22,50],"timbre":[24],"of":[25,31,54,61,69,80,125,190],"source":[27,57,127],"singer":[28,34,58,191],"into":[29,59],"target":[33,64,129],"without":[35],"using":[36,140],"vocoder":[38],"to":[39,49,78,86,175,194],"generate":[40],"converted":[41,71,182],"waveforms.":[44],"SVC":[45],"makes":[46,172],"it":[47,173],"possible":[48,174],"characteristics":[53],"an":[55,62],"arbitrary":[56,63],"those":[60],"singer.":[65],"However,":[66],"speech":[67,178],"quality":[68,179],"is":[74,137,148],"significantly":[75,176],"degraded":[76],"compared":[77,193],"natural":[82],"due":[85],"various":[87],"factors,":[88],"such":[89],"as":[90,156],"analysis":[91],"and":[92,128],"modeling":[93],"errors":[94],"in":[95,114,122,160,180],"vocoderbased":[97],"framework.":[98],"To":[99],"alleviate":[100],"this":[101],"degradation,":[102],"we":[103],"propose":[104],"process":[108],"directly":[110,138],"modifies":[111],"signal":[113],"domain":[117],"by":[118],"estimating":[119],"difference":[121],"spectra":[124],"singers\u2019":[130],"voices.":[132],"The":[133,164],"spectral":[135,210],"feature":[136],"estimated":[139],"Gaussian":[143,206],"mixture":[144,207],"model":[145,159],"(GMM)":[146],"analytically":[149],"derived":[150],"from":[151],"traditional":[153],"GMM":[154],"used":[155],"conventional":[162,196],"SVC.":[163,197],"experimental":[165],"results":[166],"demonstrate":[167],"proposed":[170],"method":[171],"improve":[177],"while":[185],"preserving":[186],"accuracy":[189],"identity":[192],"Index":[198],"Terms:":[199],"voice,":[201],"conversion,":[204],"vocoder,":[205],"model,":[208],"compensation":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}