{"id":"https://openalex.org/W2131220060","doi":"https://doi.org/10.1109/icassp.2011.5947371","title":"Improved F0 modeling and generation in voice conversion","display_name":"Improved F0 modeling and generation in voice conversion","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2131220060","doi":"https://doi.org/10.1109/icassp.2011.5947371","mag":"2131220060"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5016675592","display_name":"Aki Kunikoshi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["CN","JP"],"is_corresponding":false,"raw_author_name":"Aki Kunikoshi","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342006","display_name":"Yao Qian","orcid":"https://orcid.org/0000-0003-1855-9630"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Qian","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank Soong","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["University of Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4568","last_page":"4571"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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":0.9883999824523926,"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/speech-recognition","display_name":"Speech recognition","score":0.704718291759491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6015718579292297},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.5966424942016602},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5625916719436646},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.48939624428749084},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48692381381988525},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44711679220199585},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4332776367664337},{"id":"https://openalex.org/keywords/discontinuity","display_name":"Discontinuity (linguistics)","score":0.41777271032333374},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3873664140701294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29218846559524536},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26328277587890625}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.704718291759491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6015718579292297},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.5966424942016602},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5625916719436646},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.48939624428749084},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48692381381988525},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44711679220199585},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4332776367664337},{"id":"https://openalex.org/C2777042112","wikidata":"https://www.wikidata.org/wiki/Q5281658","display_name":"Discontinuity (linguistics)","level":2,"score":0.41777271032333374},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3873664140701294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29218846559524536},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26328277587890625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947371","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947371","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.378.585","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.378.585","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2011/ICASSP_p4568-4571_t2011-5.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1979449467","https://openalex.org/W2000513720","https://openalex.org/W2085245374","https://openalex.org/W2100351502","https://openalex.org/W2103279870","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2156142001"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W4285526294","https://openalex.org/W2313188200","https://openalex.org/W1975015735"],"abstract_inverted_index":{"F0":[0,14,53,117,126],"is":[1,15,159],"an":[2,12,30,87,121],"acoustic":[3],"feature":[4,118,123],"that":[5,28,156],"varies":[6],"largely":[7],"from":[8,116],"one":[9],"speaker":[10,179],"to":[11,32,48,103],"other.":[13],"characterized":[16,107],"by":[17,108],"a":[18,56,70,78,93],"discontinuity":[19],"in":[20,37,55,86,92,132,148,161],"the":[21,61,109,129,133,157,163,169],"transition":[22],"between":[23],"voiced":[24,52,75],"and":[25,51,77,128,151,177],"unvoiced":[26,50,82],"sounds":[27],"presents":[29],"obstacle":[31],"GMM":[33],"modeling":[34,127],"for":[35,68,74,81,124,171],"use":[36,62,104],"voice":[38,136,145],"conversion.":[39,137],"A":[40],"Multi-Space":[41],"Distribution":[42],"(MSD)":[43],"[5]":[44],"can":[45],"be":[46],"used":[47],"model":[49],"regions":[54],"linearly":[57],"weighted":[58],"mixture.":[59],"However,":[60],"of":[63,135],"two":[64],"incompatible":[65],"probabilistic":[66],"spaces,":[67],"example":[69],"continuous":[71],"probability":[72,80],"density":[73],"observations,":[76,83],"discrete":[79],"may":[84],"result":[85],"imprecise":[88],"voiced/unvoiced":[89],"(v/u)":[90],"conversion":[91,146],"maximum":[94],"likelihood":[95],"(ML)":[96],"sense.":[97],"In":[98],"this":[99],"paper":[100],"we":[101],"propose":[102],"voicing":[105],"strength,":[106],"normalized":[110],"correlation":[111],"coefficient":[112],"magnitude,":[113],"as":[114,120],"calculated":[115],"extraction,":[119],"additional":[122],"improving":[125],"v/u":[130],"decision":[131],"context":[134],"The":[138],"proposed":[139],"method":[140],"was":[141],"evaluated":[142],"on":[143],"male-to-female":[144],"tasks":[147],"both":[149],"Mandarin":[150],"English.":[152],"Objective":[153],"tests":[154,181],"showed":[155,183],"approach":[158],"effective":[160],"reducing":[162],"Root":[164],"Mean":[165],"Square":[166],"Error,":[167],"while":[168],"results":[170],"subjective":[172],"metrics":[173],"including":[174],"AB":[175],"preference":[176],"ABX":[178],"similarity":[180],"also":[182],"gains.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}