{"id":"https://openalex.org/W3096359985","doi":"https://doi.org/10.21437/interspeech.2020-2559","title":"Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling","display_name":"Cyclic Spectral Modeling for Unsupervised Unit Discovery into Voice Conversion with Excitation and Waveform Modeling","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096359985","doi":"https://doi.org/10.21437/interspeech.2020-2559","mag":"3096359985"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2559","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2559","pdf_url":"https://www.isca-archive.org/interspeech_2020/tobing20_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2020/tobing20_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4861","last_page":"4865"},"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":0.998199999332428,"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":0.9939000010490417,"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/waveform","display_name":"Waveform","score":0.7640396952629089},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6172740459442139},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.588169515132904},{"id":"https://openalex.org/keywords/excitation","display_name":"Excitation","score":0.4812740683555603},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4446808695793152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3851120173931122},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14730742573738098},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1417536437511444},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1104544997215271},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08289310336112976}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7640396952629089},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6172740459442139},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.588169515132904},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.4812740683555603},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4446808695793152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3851120173931122},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14730742573738098},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1417536437511444},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1104544997215271},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08289310336112976},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2559","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2559","pdf_url":"https://www.isca-archive.org/interspeech_2020/tobing20_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2020-2559","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2559","pdf_url":"https://www.isca-archive.org/interspeech_2020/tobing20_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1688345242","display_name":"Next generation speech translation research","funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7789893098","display_name":null,"funder_award_id":"JP-MJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096359985.pdf","grobid_xml":"https://content.openalex.org/works/W3096359985.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2025482506","https://openalex.org/W2055408826","https://openalex.org/W2134202996","https://openalex.org/W2346964103","https://openalex.org/W2347098582","https://openalex.org/W2395899413","https://openalex.org/W2406349064","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2547039119","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2787447541","https://openalex.org/W2940544976","https://openalex.org/W2946555236","https://openalex.org/W2963620343","https://openalex.org/W2964115348","https://openalex.org/W2964121744","https://openalex.org/W2972374322","https://openalex.org/W2972544500","https://openalex.org/W2972867623","https://openalex.org/W3015878662"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2883092465","https://openalex.org/W2114441484"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,42,55,93,117,124,133,160,166,172],"novel":[3],"approach":[4],"of":[5,12,74,99,158,164,170,176,181],"cyclic":[6,31,37,61,71],"spectral":[7,27,75,86],"modeling":[8,28,120,143],"for":[9,48,127,136,150,178],"unsupervised":[10],"discovery":[11],"speech":[13,50,139,184],"units":[14],"into":[15],"voice":[16,188],"conversion":[17,105,189],"with":[18,116],"excitation":[19],"network":[20],"and":[21,35,69,155],"waveform":[22,142],"modeling.Specifically,":[23],"we":[24],"propose":[25],"two":[26],"techniques:":[29],"1)":[30],"vectorquantized":[32],"autoencoder":[33,39],"(CycleVQVAE),":[34],"2)":[36],"variational":[38],"(CycleVAE).In":[40],"CycleVQVAE,":[41,128],"discrete":[43],"latent":[44,57,96],"space":[45,58,97,113],"is":[46,59,63,80,89,114,121,131,144,148,156],"used":[47,90],"the":[49,66,70,78,84,109,151,179,182,186],"units,":[51],"whereas,":[52],"in":[53,123,132,185],"Cycle-VAE,":[54],"continuous":[56],"used.The":[60,145],"structure":[62],"developed":[64,122],"using":[65],"reconstruction":[67,72],"flow":[68,73],"features,":[76],"where":[77],"latter":[79],"obtained":[81],"by":[82],"recycling":[83],"converted":[85,183],"features.This":[87],"method":[88],"to":[91],"obtain":[92],"possible":[94,103],"speaker-independent":[95],"because":[98],"marginalization":[100],"on":[101],"all":[102],"speaker":[104,167],"pairs":[106],"during":[107],"training.On":[108],"other":[110],"hand,":[111],"speaker-dependent":[112],"conditioned":[115],"one-hot":[118],"speaker-code.Excitation":[119],"separate":[125],"manner":[126,135],"while":[129],"it":[130],"joint":[134],"CycleVAE.To":[137],"generate":[138],"waveform,":[140],"WaveNet-based":[141],"proposed":[146],"framework":[147],"entried":[149],"ZeroSpeech":[152],"Challenge":[153],"2020,":[154],"capable":[157],"reaching":[159],"character":[161],"error":[162],"rate":[163],"0.21,":[165],"similarity":[168],"score":[169,175],"3.91,":[171],"mean":[173],"opinion":[174],"3.84":[177],"naturalness":[180],"2019":[187],"task.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
