{"id":"https://openalex.org/W51255321","doi":"https://doi.org/10.21437/interspeech.2008-560","title":"A comparison of voice conversion methods for transforming voice quality in emotional speech synthesis","display_name":"A comparison of voice conversion methods for transforming voice quality in emotional speech synthesis","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W51255321","doi":"https://doi.org/10.21437/interspeech.2008-560","mag":"51255321"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-560","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/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"],"is_corresponding":false,"raw_author_name":"Oytun T\u00fcrk","raw_affiliation_strings":["German Research Centre for Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Centre for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110281069","display_name":"Marc L. Schr\u00f6der","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Marc Schr\u00f6der","raw_affiliation_strings":["German Research Centre for Artificial Intelligence, Kaiserslautern, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Centre for Artificial Intelligence, Kaiserslautern, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.702,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.9418276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2282","last_page":"2285"},"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":0.9986000061035156,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.8611153364181519},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7351045608520508},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.730383574962616},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5829387903213501},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5147719383239746},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4948217272758484},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4874999225139618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2957548499107361},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13764071464538574},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.09706911444664001}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8611153364181519},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351045608520508},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.730383574962616},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5829387903213501},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5147719383239746},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4948217272758484},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4874999225139618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2957548499107361},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13764071464538574},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.09706911444664001},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2008-560","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.139.6188","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.139.6188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dfki.de/~schroed/articles/turk_schroeder2008.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W32964811","https://openalex.org/W33533989","https://openalex.org/W1493077701","https://openalex.org/W1581153084","https://openalex.org/W1588037970","https://openalex.org/W1991402032","https://openalex.org/W2067234399","https://openalex.org/W2118850452","https://openalex.org/W2123003832","https://openalex.org/W2139052928","https://openalex.org/W2156142001","https://openalex.org/W2188791853","https://openalex.org/W2428180336"],"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/W2736714427","https://openalex.org/W2163679795","https://openalex.org/W2136885550","https://openalex.org/W2371908859","https://openalex.org/W127416991"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,38,136],"comparison":[4],"of":[5],"methods":[6,98],"for":[7,65],"transforming":[8,66],"voice":[9,49,69,82],"quality":[10],"in":[11,32,42,88,100,103,129,135],"neutral":[12,40],"synthetic":[13],"speech":[14,24],"to":[15,52,106],"match":[16,53],"cheerful,":[17],"aggressive,":[18],"and":[19,37,79,115],"depressed":[20],"expressive":[21,56,108,133],"styles.":[22],"Neutral":[23],"is":[25,46],"generated":[26],"using":[27,48],"the":[28,33,54,58,67,74,124,131],"unit":[29],"selection":[30],"system":[31],"MARY":[34],"TTS":[35,109],"platform":[36],"large":[39],"database":[41],"German.":[43],"The":[44],"output":[45],"modified":[47],"conversion":[50,64,83],"techniques":[51],"target":[55,107,132],"styles,":[57],"focus":[59],"being":[60],"on":[61],"spectral":[62],"envelope":[63],"overall":[68],"quality.":[70],"Various":[71],"improvements":[72],"over":[73],"state-of-the-art":[75],"weighted":[76,112,125],"codebook":[77,126],"mapping":[78,114,127],"GMM":[80,116],"based":[81,117],"frameworks":[84],"are":[85],"employed":[86],"resulting":[87],"three":[89,97],"algorithms.":[90],"Objective":[91],"evaluation":[92],"results":[93],"show":[94],"that":[95],"all":[96],"result":[99],"comparable":[101],"reduction":[102],"objective":[104],"distance":[105],"outputs":[110,128],"whereas":[111],"frame":[113],"transformations":[118],"were":[119],"perceived":[120],"slightly":[121],"better":[122],"than":[123],"generating":[130],"style":[134],"listening":[137],"test.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
