{"id":"https://openalex.org/W6967501445","doi":"https://doi.org/10.5281/zenodo.10265377","title":"Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables","display_name":"Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6967501445","doi":"https://doi.org/10.5281/zenodo.10265377"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chin-Yun Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chin-Yun Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gy\u00f6rgy Fazekas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38099793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3617999851703644,"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":0.3617999851703644,"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/T10863","display_name":"Voice and Speech Disorders","score":0.21699999272823334,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.1647000014781952,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/interpretability","display_name":"Interpretability","score":0.8334000110626221},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7998999953269958},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6563000082969666},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.5593000054359436},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4763999879360199},{"id":"https://openalex.org/keywords/infinite-impulse-response","display_name":"Infinite impulse response","score":0.4237000048160553},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.421099990606308},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.37779998779296875}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8334000110626221},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424000263214111},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.5593000054359436},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C183816354","wikidata":"https://www.wikidata.org/wiki/Q665617","display_name":"Infinite impulse response","level":4,"score":0.4237000048160553},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.2669999897480011}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265377","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265377","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"GlOttal-flow":[3],"LPC":[4],"Filter":[5],"(GOLF),":[6],"a":[7,31,106],"novel":[8],"method":[9],"for":[10,79,99],"singing":[11,60,103],"voice":[12,23,61,122],"synthesis":[13,65],"(SVS)":[14],"that":[15,84],"exploits":[16],"the":[17,21,35,43,88,92,112,116,120,128],"physical":[18,117],"characteristics":[19],"of":[20,76,91,114,119,130],"human":[22,93,121],"using":[24],"differentiable":[25,107],"digital":[26],"signal":[27],"processing.":[28],"GOLF":[29,85],"employs":[30],"glottal":[32],"model":[33,87],"as":[34],"harmonic":[36],"source":[37],"and":[38,50,67,72,101,126,137],"IIR":[39],"filters":[40],"to":[41,70],"simulate":[42],"vocal":[44],"tract,":[45],"resulting":[46],"in":[47,105,139],"an":[48,74],"interpretable":[49],"efficient":[51],"approach.":[52],"We":[53],"show":[54],"it":[55],"is":[56],"competitive":[57],"with":[58],"state-of-the-art":[59],"vocoders,":[62],"requiring":[63],"fewer":[64],"parameters":[66],"less":[68],"memory":[69],"train,":[71],"runs":[73],"order":[75],"magnitude":[77],"faster":[78],"inference.":[80],"Additionally,":[81],"we":[82],"demonstrate":[83],"can":[86],"phase":[89],"components":[90],"voice,":[94],"which":[95,133],"has":[96],"immense":[97],"potential":[98],"rendering":[100],"analysing":[102],"voices":[104],"manner.":[108],"Our":[109],"results":[110],"highlight":[111],"effectiveness":[113],"incorporating":[115],"properties":[118],"mechanism":[123],"into":[124],"SVS":[125],"underscore":[127],"advantages":[129],"signal-processing-based":[131],"approaches,":[132],"offer":[134],"greater":[135],"interpretability":[136],"efficiency":[138],"synthesis.":[140]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}