{"id":"https://openalex.org/W4372266960","doi":"https://doi.org/10.1109/icassp49357.2023.10095565","title":"A Unified One-Shot Prosody and Speaker Conversion System with Self-Supervised Discrete Speech Units","display_name":"A Unified One-Shot Prosody and Speaker Conversion System with Self-Supervised Discrete Speech Units","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266960","doi":"https://doi.org/10.1109/icassp49357.2023.10095565"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rudnicky","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute","Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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":0.9925000071525574,"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/prosody","display_name":"Prosody","score":0.9341624975204468},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8241926431655884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7182890176773071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6474025249481201},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6202561855316162},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5614280104637146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49517789483070374},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.44405263662338257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4365427494049072}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.9341624975204468},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8241926431655884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182890176773071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6474025249481201},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6202561855316162},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5614280104637146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49517789483070374},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.44405263662338257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4365427494049072},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W181056519","https://openalex.org/W2143827132","https://openalex.org/W2187089797","https://openalex.org/W2593414223","https://openalex.org/W2945478979","https://openalex.org/W2946200149","https://openalex.org/W2947445680","https://openalex.org/W2962866891","https://openalex.org/W2972359262","https://openalex.org/W2973049979","https://openalex.org/W2998572311","https://openalex.org/W3015805741","https://openalex.org/W3016160783","https://openalex.org/W3034794073","https://openalex.org/W3036601975","https://openalex.org/W3092028330","https://openalex.org/W3096524539","https://openalex.org/W3163573274","https://openalex.org/W3169739675","https://openalex.org/W3197659778","https://openalex.org/W3198217962","https://openalex.org/W3205631867","https://openalex.org/W3207300132","https://openalex.org/W3209059054","https://openalex.org/W4225939199","https://openalex.org/W4287887366","https://openalex.org/W4296068587","https://openalex.org/W4301371414","https://openalex.org/W4361994820","https://openalex.org/W6607364320","https://openalex.org/W6762533536","https://openalex.org/W6763832098","https://openalex.org/W6772349387","https://openalex.org/W6776390925","https://openalex.org/W6780218876","https://openalex.org/W6780226713","https://openalex.org/W6783867762","https://openalex.org/W6796577156","https://openalex.org/W6803547063","https://openalex.org/W6809829207"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W169399214","https://openalex.org/W4214652783","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W3100825170","https://openalex.org/W258725851"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,61,100],"unified":[3],"system":[4,64,84,134],"to":[5,30],"realize":[6],"one-shot":[7],"voice":[8],"conversion":[9],"(VC)":[10],"on":[11,121],"the":[12,22,31,39,93,97,113,122],"pitch,":[13,104],"rhythm,":[14],"and":[15,26,89,106,127,143,147],"speaker":[16,90,125,141],"attributes.":[17],"Existing":[18],"works":[19],"generally":[20],"ignore":[21],"correlation":[23],"between":[24],"prosody":[25,88,98,101,144],"language":[27,43,51,71],"content,":[28],"leading":[29],"degradation":[32],"of":[33,41],"naturalness":[34],"in":[35,112,138],"converted":[36],"speech.":[37],"Additionally,":[38],"lack":[40],"proper":[42],"features":[44],"prevents":[45],"these":[46,57],"systems":[47],"from":[48,92],"accurately":[49],"preserving":[50],"content":[52],"after":[53],"conversion.":[54],"To":[55],"address":[56],"issues,":[58],"we":[59],"devise":[60],"cascaded":[62],"modular":[63],"leveraging":[65],"self-supervised":[66],"discrete":[67,74,110,128],"speech":[68,119],"units":[69,75],"as":[70],"representation.":[72],"These":[73],"provide":[76],"duration":[77,107],"information":[78],"essential":[79],"for":[80,108],"rhythm":[81],"modeling.":[82],"Our":[83],"first":[85],"extracts":[86],"utterance-level":[87],"representations":[91],"raw":[94],"waveform.":[95],"Given":[96],"representation,":[99,126],"predictor":[102],"estimates":[103],"energy,":[105],"each":[109],"unit":[111],"utterance.":[114],"A":[115],"synthesizer":[116],"further":[117],"reconstructs":[118],"based":[120],"predicted":[123],"prosody,":[124],"units.":[129],"Experiments":[130],"show":[131],"that":[132],"our":[133],"outperforms":[135],"previous":[136],"approaches":[137],"naturalness,":[139],"intelligibility,":[140],"transferability,":[142],"transferability.":[145],"Code":[146],"samples":[148],"are":[149],"publicly":[150],"available.":[151],"<sup":[152],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[154]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
