{"id":"https://openalex.org/W2402356521","doi":"https://doi.org/10.1109/icassp.2016.7472761","title":"Cute: A concatenative method for voice conversion using exemplar-based unit selection","display_name":"Cute: A concatenative method for voice conversion using exemplar-based unit selection","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2402356521","doi":"https://doi.org/10.1109/icassp.2016.7472761","mag":"2402356521"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]},{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA","Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034842939","display_name":"Adam Finkelstein","orcid":"https://orcid.org/0000-0001-9422-5363"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Finkelstein","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036534746","display_name":"Stephen DiVerdi","orcid":"https://orcid.org/0000-0002-6694-3381"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen DiVerdi","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085050428","display_name":"Jingwan Lu","orcid":"https://orcid.org/0000-0002-3598-9918"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingwan Lu","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044614923","display_name":"Gautham J. Mysore","orcid":"https://orcid.org/0000-0003-0483-9252"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautham J. Mysore","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100702050"],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":6.8556,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.96888839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5660","last_page":"5664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.8414034843444824},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.767951488494873},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6223833560943604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5931745767593384},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5696859359741211},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5459245443344116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4722929298877716},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46612998843193054},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4323662519454956},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38178640604019165},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1800348162651062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07011130452156067},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0698261559009552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414034843444824},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.767951488494873},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6223833560943604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5931745767593384},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5696859359741211},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5459245443344116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4722929298877716},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46612998843193054},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4323662519454956},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38178640604019165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1800348162651062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07011130452156067},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0698261559009552},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W59175527","https://openalex.org/W95152782","https://openalex.org/W146976060","https://openalex.org/W1517202054","https://openalex.org/W1570629387","https://openalex.org/W1604034532","https://openalex.org/W1741199358","https://openalex.org/W1965912016","https://openalex.org/W2049686551","https://openalex.org/W2051903221","https://openalex.org/W2091425152","https://openalex.org/W2100649345","https://openalex.org/W2120605154","https://openalex.org/W2121095010","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2142384583","https://openalex.org/W2147152002","https://openalex.org/W2152974894","https://openalex.org/W2296422624","https://openalex.org/W3123895079","https://openalex.org/W6602447803","https://openalex.org/W6603838645","https://openalex.org/W6637576829","https://openalex.org/W6682013673","https://openalex.org/W6697695168"],"related_works":["https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W1972035260","https://openalex.org/W2383646825","https://openalex.org/W2371018915","https://openalex.org/W2354191502","https://openalex.org/W1972225038","https://openalex.org/W3134658850","https://openalex.org/W2355938171","https://openalex.org/W127416991"],"abstract_inverted_index":{"State-of-the":[0],"art":[1],"voice":[2,6],"conversion":[3],"methods":[4],"re-synthesize":[5],"from":[7,38,49],"spectral":[8],"representations":[9],"such":[10],"as":[11,43,45],"MFCCs":[12],"and":[13,40,73,91,99],"STRAIGHT,":[14],"thereby":[15],"introducing":[16],"muffled":[17],"artifacts.":[18],"We":[19],"propose":[20],"a":[21,46],"method":[22,53,112],"that":[23,95,109],"circumvents":[24],"this":[25],"concern":[26],"using":[27,69],"concatenative":[28],"synthesis":[29],"coupled":[30],"with":[31],"exemplar-based":[32],"unit":[33,85],"selection.":[34],"Given":[35],"parallel":[36],"speech":[37],"source":[39],"target":[41,59],"speakers":[42],"well":[44],"new":[47],"query":[48],"the":[50,58,67,77,88,110],"source,":[51],"our":[52],"stitches":[54],"together":[55],"pieces":[56],"of":[57,102],"voice.":[60],"It":[61],"optimizes":[62],"for":[63],"three":[64],"goals:":[65],"matching":[66],"query,":[68],"long":[70],"consecutive":[71],"segments,":[72],"smooth":[74],"transitions":[75],"between":[76],"segments.":[78],"To":[79],"achieve":[80],"these":[81],"goals,":[82],"we":[83],"perform":[84],"selection":[86,101],"at":[87],"frame":[89],"level":[90],"introduce":[92],"triphone-based":[93],"preselection":[94],"greatly":[96],"reduces":[97],"computation":[98],"enforces":[100],"long,":[103],"contiguous":[104],"pieces.":[105],"Our":[106],"experiments":[107],"show":[108],"proposed":[111],"has":[113],"better":[114],"quality":[115],"than":[116],"baseline":[117],"methods,":[118],"while":[119],"preserving":[120],"high":[121],"individuality.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}