{"id":"https://openalex.org/W2009226274","doi":"https://doi.org/10.1109/icassp.2009.4960404","title":"Application of voice conversion for cross-language rap singing transformation","display_name":"Application of voice conversion for cross-language rap singing transformation","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2009226274","doi":"https://doi.org/10.1109/icassp.2009.4960404","mag":"2009226274"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5046810738","display_name":"Oytun T\u00fcrk","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]},{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE","TR"],"is_corresponding":true,"raw_author_name":"Oytun Turk","raw_affiliation_strings":["Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","ITU Ayazaga Kampusu, ARI-I Teknopark Binasi, Sestek, Inc., Istanbul, Turkey","Speech Group, DFKI GmbH Language Technology Lab, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"ITU Ayazaga Kampusu, ARI-I Teknopark Binasi, Sestek, Inc., Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]},{"raw_affiliation_string":"Speech Group, DFKI GmbH Language Technology Lab, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079547173","display_name":"Osman B\u00fcy\u00fck","orcid":"https://orcid.org/0000-0003-1039-3234"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["DE","TR"],"is_corresponding":false,"raw_author_name":"Osman Buyuk","raw_affiliation_strings":["Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey","Speech Group, DFKI GmBH Language Technology Laboratory, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]},{"raw_affiliation_string":"Speech Group, DFKI GmBH Language Technology Laboratory, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050368406","display_name":"Ali Haznedaro\u011flu","orcid":"https://orcid.org/0000-0002-1690-531X"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]},{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ali Haznedaroglu","raw_affiliation_strings":["Electrical and Electronics Eng. Dept., Bogazici University, Istanbul, Turkey","Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Electrical and Electronics Eng. Dept., Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017246112","display_name":"Levent M. Arslan","orcid":"https://orcid.org/0000-0002-6086-8018"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]},{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]},{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE","TR"],"is_corresponding":false,"raw_author_name":"Levent M. Arslan","raw_affiliation_strings":["Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey","Speech Group, DFKI GmBH Language Technology Laboratory, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Electronics and Electronics Engineering Department, Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]},{"raw_affiliation_string":"Sestek Inc., ITU Ayazaga Kampusu, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]},{"raw_affiliation_string":"Speech Group, DFKI GmBH Language Technology Laboratory, Berlin, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046810738"],"corresponding_institution_ids":["https://openalex.org/I33256026","https://openalex.org/I4405392","https://openalex.org/I48912391"],"apc_list":null,"apc_paid":null,"fwci":1.8094,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87143855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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":0.8132853507995605},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.7835370302200317},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7793972492218018},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6265817284584045},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.599276065826416},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5593817234039307},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48058605194091797},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4712883532047272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3880263566970825},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15838095545768738},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14053699374198914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132853507995605},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7835370302200317},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7793972492218018},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6265817284584045},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.599276065826416},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5593817234039307},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48058605194091797},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4712883532047272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3880263566970825},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15838095545768738},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14053699374198914},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:de90d156-608e-44f3-9188-20f374b8e750","is_oa":false,"landing_page_url":"https://avesis.kocaeli.edu.tr/publication/details/de90d156-608e-44f3-9188-20f374b8e750/oai","pdf_url":null,"source":{"id":"https://openalex.org/S7407055291","display_name":"Kocaeli \u00dcniversitesi - AVES\u0130S","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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W9388558","https://openalex.org/W51255321","https://openalex.org/W1566744681","https://openalex.org/W1592940279","https://openalex.org/W1991402032","https://openalex.org/W2013996527","https://openalex.org/W2067234399","https://openalex.org/W2094384760","https://openalex.org/W2118850452","https://openalex.org/W2129812225","https://openalex.org/W2130544847","https://openalex.org/W2146927751","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2186590435","https://openalex.org/W2398195097","https://openalex.org/W4285719527","https://openalex.org/W6600383931","https://openalex.org/W6633899882","https://openalex.org/W6635329185","https://openalex.org/W6712495231"],"related_works":["https://openalex.org/W2293149949","https://openalex.org/W2026099691","https://openalex.org/W4284672201","https://openalex.org/W2377486419","https://openalex.org/W2943202426","https://openalex.org/W2950156284","https://openalex.org/W2736714427","https://openalex.org/W2163679795","https://openalex.org/W2137816434","https://openalex.org/W2017956276"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,38,61],"enables":[2],"generation":[3],"of":[4,12,32,70,104,121,145],"a":[5,21,80,101,107],"desired":[6],"speaker's":[7],"voice":[8,37,60],"from":[9,44,100],"audio":[10],"recordings":[11],"another":[13],"speaker.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18],"focus":[19],"on":[20],"music":[22,33],"application":[23],"and":[24,67,115,141],"describe":[25],"the":[26,71,89,146],"first":[27,77],"steps":[28],"towards":[29],"generating":[30],"voices":[31],"celebrities":[34],"using":[35,50],"conventional":[36],"techniques.":[39],"Specifically,":[40],"rap":[41],"singing":[42],"transformations":[43],"English":[45],"to":[46,87,112,116,138],"Spanish":[47],"are":[48,74],"performed":[49],"parallel":[51],"training":[52],"material":[53],"in":[54],"English.":[55],"Weighted":[56],"codebook":[57],"mapping":[58],"based":[59],"with":[62],"two":[63],"different":[64],"alignment":[65,147],"methods":[66],"temporal":[68],"smoothing":[69,108,133],"transformation":[72],"filter":[73],"employed.":[75],"The":[76,93,119,131],"aligner":[78,95],"uses":[79],"HMM":[81],"trained":[82,99],"for":[83],"each":[84],"source":[85],"recording":[86],"force-align":[88],"corresponding":[90],"target":[91,139],"recording.":[92],"second":[94],"employs":[96],"speaker-independent":[97],"HMMs":[98],"large":[102],"number":[103],"speakers.":[105],"Additionally,":[106],"step":[109],"is":[110],"devised":[111],"reduce":[113],"discontinuities":[114],"improve":[117],"performance.":[118],"results":[120],"subjective":[122],"evaluations":[123],"indicate":[124],"that":[125],"both":[126,136],"aligners":[127],"perform":[128],"equivalently":[129],"well.":[130],"proposed":[132],"technique":[134],"improves":[135],"similarity":[137],"singer":[140],"quality":[142],"significantly":[143],"regardless":[144],"method.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}
