{"id":"https://openalex.org/W2296422624","doi":"https://doi.org/10.21437/interspeech.2013-667","title":"Exemplar-based unit selection for voice conversion utilizing temporal information","display_name":"Exemplar-based unit selection for voice conversion utilizing temporal information","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2296422624","doi":"https://doi.org/10.21437/interspeech.2013-667","mag":"2296422624"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-667","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhizheng Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043168931","display_name":"Tomi Kinnunen","orcid":"https://orcid.org/0000-0002-4371-7322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomi Kinnunen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.4615,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.96078431,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3057","last_page":"3061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9944999814033508,"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":0.8064862489700317},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7215207815170288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6667093634605408},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5867441892623901},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5263996124267578},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5219290256500244},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48593512177467346},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.474764347076416},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.46076464653015137},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42650681734085083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4188510477542877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11139515042304993},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10911121964454651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8064862489700317},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7215207815170288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6667093634605408},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5867441892623901},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5263996124267578},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5219290256500244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48593512177467346},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.474764347076416},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.46076464653015137},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42650681734085083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4188510477542877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11139515042304993},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10911121964454651},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2013-667","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-667","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.624","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.624","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/exemplar_unit_selection_IS2013.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.709.6929","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.6929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.uef.fi/sipu/pub/IS130293.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W33533989","https://openalex.org/W1969728648","https://openalex.org/W1972420736","https://openalex.org/W2005438552","https://openalex.org/W2023952145","https://openalex.org/W2049686551","https://openalex.org/W2097207027","https://openalex.org/W2100649345","https://openalex.org/W2105160541","https://openalex.org/W2110118271","https://openalex.org/W2114543868","https://openalex.org/W2120605154","https://openalex.org/W2121095010","https://openalex.org/W2141520175","https://openalex.org/W2150658333","https://openalex.org/W2152974894","https://openalex.org/W2156142001","https://openalex.org/W2157412983"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2054007705","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W205537210"],"abstract_inverted_index":{"Although":[0],"temporal":[1,33,57,147],"information":[2,58,148],"of":[3,16,27],"speech":[4,23,69],"has":[5],"been":[6],"shown":[7],"to":[8,67],"play":[9],"an":[10],"important":[11],"role":[12],"in":[13,83,98],"perception,":[14],"most":[15],"the":[17,22,32,95,99,119],"voice":[18,61],"conver-sion":[19,62],"approaches":[20],"assume":[21],"frames":[24,50,66],"are":[25],"independent":[26],"each":[28],"other,":[29],"thereby":[30],"ignoring":[31],"information.":[34],"In":[35],"this":[36],"study,":[37],"we":[38],"improve":[39],"conventional":[40,84,135],"unit":[41,85,136,143],"selection":[42,137],"approach":[43,72],"by":[44,63,110],"us-ing":[45],"exemplars":[46],"which":[47],"span":[48],"multiple":[49],"as":[51],"base":[52],"units,":[53],"and":[54,79,124,134],"also":[55,91],"take":[56],"constraint":[59],"into":[60],"using":[64,112],"overlapping":[65],"generate":[68],"parame-ters.":[70],"This":[71],"thus":[73],"provides":[74],"more":[75],"stable":[76],"concatenation":[77],"cost":[78],"avoids":[80],"discontinuity":[81],"problem":[82,97],"se-lection":[86],"approach.":[87],"The":[88],"proposed":[89,130],"method":[90,109,131],"keeps":[92],"away":[93],"from":[94],"over-smoothing":[96],"mainstream":[100],"joint":[101],"density":[102],"Gaussian":[103],"mixture":[104],"model":[105],"(JD-GMM)":[106],"based":[107],"conversion":[108],"directly":[111],"target":[113],"speaker\u2019s":[114],"training":[115],"data":[116],"for":[117],"synthesizing":[118],"converted":[120],"speech.":[121],"Both":[122],"objective":[123],"subjective":[125],"evaluations":[126],"indicate":[127],"that":[128],"our":[129],"outperforms":[132],"JD-GMM":[133],"methods.":[138],"Index":[139],"Terms:":[140],"Voice":[141],"conversion,":[142],"selection,":[144],"multi-frame":[145],"ex-emplar,":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}