{"id":"https://openalex.org/W188951208","doi":"https://doi.org/10.21437/interspeech.2010-497","title":"Text-independent F0 transformation with non-parallel data for voice conversion","display_name":"Text-independent F0 transformation with non-parallel data for voice conversion","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W188951208","doi":"https://doi.org/10.21437/interspeech.2010-497","mag":"188951208"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/24457321/erro07a.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhi-Zheng Wu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["University of Eastern Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Eastern Finland","institution_ids":["https://openalex.org/I175532246","https://openalex.org/I4210107997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Agency for Science, Technology and Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research","institution_ids":["https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9073,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.86020884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1732","last_page":"1735"},"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":0.9980000257492065,"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":0.9922000169754028,"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/computer-science","display_name":"Computer science","score":0.8130706548690796},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7023267149925232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6324881315231323},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6165537238121033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6005672812461853},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5207064747810364},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5046712160110474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956838548183441},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37056320905685425},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3253612518310547},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06856533885002136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8130706548690796},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7023267149925232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6324881315231323},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6165537238121033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6005672812461853},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5207064747810364},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5046712160110474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956838548183441},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37056320905685425},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3253612518310547},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06856533885002136},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-497","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c5945ecf-1f74-461f-9dc0-401aa28617eb","is_oa":true,"landing_page_url":"http://www.interspeech2010.jpn.org/","pdf_url":"https://www.pure.ed.ac.uk/ws/files/24457321/erro07a.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.178.6294","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.178.6294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.joensuu.fi/pages/tkinnu/webpage/pdf/IS2010_ProsodyConversion.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c5945ecf-1f74-461f-9dc0-401aa28617eb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c5945ecf-1f74-461f-9dc0-401aa28617eb","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kinnunen, T, Chng, E S, Li, H & Wu, Z 2010, Text-Independent F0 Transformation with Non-Parallel Data for Voice Conversion. in Interspeech 2010. pp. 2-5. < http://www.interspeech2010.jpn.org/ >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/c5945ecf-1f74-461f-9dc0-401aa28617eb","is_oa":true,"landing_page_url":"http://www.interspeech2010.jpn.org/","pdf_url":"https://www.pure.ed.ac.uk/ws/files/24457321/erro07a.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W188951208.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W33829787","https://openalex.org/W49412823","https://openalex.org/W59075858","https://openalex.org/W83932636","https://openalex.org/W95152782","https://openalex.org/W129217914","https://openalex.org/W152891837","https://openalex.org/W155193863","https://openalex.org/W156398200","https://openalex.org/W1505264225","https://openalex.org/W1520370180","https://openalex.org/W1599112982","https://openalex.org/W2013996527","https://openalex.org/W2049686551","https://openalex.org/W2067234399","https://openalex.org/W2096555739","https://openalex.org/W2100351502","https://openalex.org/W2100649345","https://openalex.org/W2112390707","https://openalex.org/W2114892915","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2136166660","https://openalex.org/W2145130307","https://openalex.org/W2153057929","https://openalex.org/W2153425803","https://openalex.org/W2156142001","https://openalex.org/W2244925781"],"related_works":["https://openalex.org/W2353644209","https://openalex.org/W2593663830","https://openalex.org/W2348743188","https://openalex.org/W2902317490","https://openalex.org/W4387423451","https://openalex.org/W2025460258","https://openalex.org/W2056619254","https://openalex.org/W2046628353","https://openalex.org/W2096879929","https://openalex.org/W3098003361"],"abstract_inverted_index":{"In":[0],"voice":[1],"conversion,":[2],"frame-level":[3,53],"mean":[4],"and":[5,19,49,83,97,112],"variance":[6],"normalization":[7,111],"is":[8,17],"typically":[9],"used":[10],"for":[11],"fundamental":[12],"frequency":[13],"(F0)":[14],"transformation,":[15],"which":[16,45],"text-independent":[18,67],"requires":[20],"no":[21],"parallel":[22,35],"training":[23,36],"data.":[24],"Some":[25],"advanced":[26],"methods":[27],"transform":[28],"pitch":[29],"contours":[30],"instead,":[31],"but":[32],"require":[33],"either":[34],"data":[37],"or":[38],"syllabic":[39],"annotations.":[40],"We":[41,59],"propose":[42],"a":[43,66],"method":[44],"retains":[46],"the":[47,52,86,101,109,113],"simplicity":[48],"text-independence":[50],"of":[51,75],"conversion":[54,82],"while":[55],"yielding":[56],"high-quality":[57],"conversion.":[58,116],"achieve":[60],"these":[61],"goals":[62],"by":[63,91],"(1)":[64],"introducing":[65],"tri-frame":[68],"alignment":[69],"method,":[70],"(2)":[71],"including":[72],"delta":[73],"features":[74],"F0":[76,92],"into":[77],"Gaussian":[78],"mixture":[79],"model":[80],"(GMM)":[81],"(3)":[84],"reducing":[85],"well-known":[87],"GMM":[88,115],"oversmoothing":[89],"effect":[90],"histogram":[93],"equalization.":[94],"Our":[95],"objective":[96],"subjective":[98],"experiments":[99],"on":[100],"CMU":[102],"Arctic":[103],"corpus":[104],"indicate":[105],"improvements":[106],"over":[107],"both":[108],"mean/variance":[110],"baseline":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}