{"id":"https://openalex.org/W4386609311","doi":"https://doi.org/10.1109/lsp.2023.3313515","title":"Rhythm Modeling for Voice Conversion","display_name":"Rhythm Modeling for Voice Conversion","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386609311","doi":"https://doi.org/10.1109/lsp.2023.3313515"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3313515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3313515","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Benjamin van Niekerk","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030861649","display_name":"Marc\u2010Andr\u00e9 Carbonneau","orcid":"https://orcid.org/0000-0002-0677-415X"},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marc-Andr\u00e9 Carbonneau","raw_affiliation_strings":["Ubisoft La Forge, Montréal, QC, Canada"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge, Montréal, QC, Canada","institution_ids":["https://openalex.org/I4210104072"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046382731"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.3479,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66028398,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"30","issue":null,"first_page":"1297","last_page":"1301"},"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":0.9988999962806702,"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":0.9983000159263611,"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/speech-recognition","display_name":"Speech recognition","score":0.781581461429596},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.752874493598938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354798913002014},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5799915194511414},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44394057989120483},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3663233518600464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32210981845855713},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07991185784339905}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.781581461429596},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.752874493598938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354798913002014},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5799915194511414},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44394057989120483},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3663233518600464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32210981845855713},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07991185784339905},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3313515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3313515","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1975216662","https://openalex.org/W2049510512","https://openalex.org/W2064218608","https://openalex.org/W2083679487","https://openalex.org/W2096774922","https://openalex.org/W2148933165","https://openalex.org/W2149569147","https://openalex.org/W2155295207","https://openalex.org/W2172080330","https://openalex.org/W2515028311","https://openalex.org/W2747874407","https://openalex.org/W2752796333","https://openalex.org/W2779206865","https://openalex.org/W2785978752","https://openalex.org/W2897353073","https://openalex.org/W2899877258","https://openalex.org/W3017502571","https://openalex.org/W3083423753","https://openalex.org/W3083776549","https://openalex.org/W3095361818","https://openalex.org/W3099078140","https://openalex.org/W3134921434","https://openalex.org/W3140429000","https://openalex.org/W3165478005","https://openalex.org/W3198134274","https://openalex.org/W3210530853","https://openalex.org/W4210699844","https://openalex.org/W4225892118","https://openalex.org/W4245896628","https://openalex.org/W4281492411","https://openalex.org/W4297841435","https://openalex.org/W4385822966","https://openalex.org/W4385823240","https://openalex.org/W6783867762","https://openalex.org/W6796575454","https://openalex.org/W6847363464","https://openalex.org/W6917585676","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W1834994814","https://openalex.org/W2981428355","https://openalex.org/W1599055764","https://openalex.org/W2041273198","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2131711534","https://openalex.org/W2289873871","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,15,44],"aims":[2],"to":[3],"transform":[4],"source":[5,60],"speech":[6,97],"into":[7,62],"a":[8],"different":[9],"target":[10,89],"voice.":[11],"However,":[12],"typical":[13],"voice":[14],"systems":[16],"do":[17],"not":[18,47],"account":[19],"for":[20,42],"rhythm,":[21],"which":[22],"is":[23],"an":[24],"important":[25],"factor":[26],"in":[27,107],"the":[28,78,88,96],"perception":[29],"of":[30,81,109],"speaker":[31],"identity.":[32],"To":[33],"bridge":[34],"this":[35],"gap,":[36],"we":[37,57,70,86],"introduce":[38],"Urhythmic\u2014an":[39],"unsupervised":[40,105],"method":[41],"rhythm":[43,72,93],"that":[45,101],"does":[46],"require":[48],"parallel":[49],"data":[50],"or":[51,77,92],"text":[52],"transcriptions.":[53],"Using":[54],"self-supervised":[55],"representations,":[56],"first":[58],"divide":[59],"audio":[61],"segments":[63],"approximating":[64],"sonorants,":[65],"obstruents,":[66],"and":[67,111],"silences.":[68],"Then":[69],"model":[71],"by":[73,94],"estimating":[74],"speaking":[75,90],"rate":[76,91],"duration":[79],"distribution":[80],"each":[82],"segment":[83],"type.":[84],"Finally,":[85],"match":[87],"time-stretching":[95],"segments.":[98],"Experiments":[99],"show":[100],"Urhythmic":[102],"outperforms":[103],"existing":[104],"methods":[106],"terms":[108],"quality":[110],"prosody.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}