{"id":"https://openalex.org/W4200027410","doi":"https://doi.org/10.1109/waspaa52581.2021.9632754","title":"End-to-End Zero-Shot Voice Conversion Using a DDSP Vocoder","display_name":"End-to-End Zero-Shot Voice Conversion Using a DDSP Vocoder","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4200027410","doi":"https://doi.org/10.1109/waspaa52581.2021.9632754"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5022048399","display_name":"Shahan Nercessian","orcid":"https://orcid.org/0000-0003-4879-7365"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shahan Nercessian","raw_affiliation_strings":["iZotope, Inc.,Cambridge,MA,USA,02139"],"affiliations":[{"raw_affiliation_string":"iZotope, Inc.,Cambridge,MA,USA,02139","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5022048399"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78847602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.7870713472366333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6174797415733337},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5420400500297546},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.49334898591041565},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4487992227077484},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44243746995925903},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4295389652252197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39296022057533264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870713472366333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6174797415733337},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5420400500297546},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.49334898591041565},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4487992227077484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44243746995925903},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4295389652252197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39296022057533264},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":38,"referenced_works":["https://openalex.org/W2296704011","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2752796333","https://openalex.org/W2805669069","https://openalex.org/W2945478979","https://openalex.org/W2962788625","https://openalex.org/W2962883485","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2972812066","https://openalex.org/W2984106626","https://openalex.org/W2989708046","https://openalex.org/W3000389243","https://openalex.org/W3046330735","https://openalex.org/W3046412268","https://openalex.org/W3047334337","https://openalex.org/W3095212898","https://openalex.org/W3095448311","https://openalex.org/W3095617022","https://openalex.org/W3096697361","https://openalex.org/W3160584619","https://openalex.org/W4298580827","https://openalex.org/W6697285287","https://openalex.org/W6726528559","https://openalex.org/W6728445508","https://openalex.org/W6745415975","https://openalex.org/W6762533536","https://openalex.org/W6770046961","https://openalex.org/W6771763809","https://openalex.org/W6781288810","https://openalex.org/W6781581198","https://openalex.org/W6784488536","https://openalex.org/W6936113694"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W3013650182","https://openalex.org/W2989283631"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,11,70],"zero-shot":[6],"voice":[7],"conversion":[8,58],"algorithm":[9,80],"using":[10],"neural":[12],"vocoder":[13,21,60],"based":[14],"on":[15],"differential":[16],"digital":[17],"signal":[18],"processing.":[19],"The":[20],"does":[22],"not":[23],"require":[24],"auto-regression,":[25],"and":[26,55,59,84],"its":[27],"lightweight,":[28],"differentiable":[29],"nature":[30],"allows":[31,56],"the":[32,44,75,78],"proposed":[33,79],"system":[34],"to":[35,62,89],"be":[36],"trained":[37],"in":[38,69],"an":[39],"end-to-end":[40],"fashion.":[41],"This":[42],"enables":[43],"use":[45],"of":[46,77,91],"more":[47],"perceptually":[48],"relevant":[49],"objective":[50],"functions":[51],"for":[52],"model":[53],"training,":[54],"feature":[57],"sub-networks":[61],"internally":[63],"learn":[64],"their":[65],"own":[66],"acoustic":[67],"representation":[68],"data-driven":[71],"manner.":[72],"We":[73],"illustrate":[74],"effectiveness":[76],"by":[81],"both":[82],"qualitative":[83],"quantitative":[85],"means,":[86],"with":[87],"comparisons":[88],"some":[90],"our":[92],"previous":[93],"works.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
