{"id":"https://openalex.org/W3193566630","doi":"https://doi.org/10.21437/ssw.2021-25","title":"Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband WaveRNN with data-driven linear prediction","display_name":"Low-latency real-time non-parallel voice conversion based on cyclic variational autoencoder and multiband WaveRNN with data-driven linear prediction","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3193566630","doi":"https://doi.org/10.21437/ssw.2021-25","mag":"3193566630"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","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/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976999759674072,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9941999912261963,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9869999885559082,"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/autoencoder","display_name":"Autoencoder","score":0.9183645248413086},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7055869698524475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.666934609413147},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5577982664108276},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39672285318374634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3956961929798126},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3804370164871216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.243784099817276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19532981514930725},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1019727885723114},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07709038257598877}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9183645248413086},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7055869698524475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.666934609413147},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5577982664108276},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39672285318374634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3956961929798126},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3804370164871216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.243784099817276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19532981514930725},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1019727885723114},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07709038257598877}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2021-25","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-25","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"}],"best_oa_location":null,"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/G6718509927","display_name":null,"funder_award_id":"CREST","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1959608418","https://openalex.org/W2013996527","https://openalex.org/W2049686551","https://openalex.org/W2056852181","https://openalex.org/W2100819376","https://openalex.org/W2120605154","https://openalex.org/W2128466129","https://openalex.org/W2161727827","https://openalex.org/W2172065531","https://openalex.org/W2187234408","https://openalex.org/W2406654659","https://openalex.org/W2471520273","https://openalex.org/W2532494225","https://openalex.org/W2749651610","https://openalex.org/W2794725088","https://openalex.org/W2962780374","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2972544500","https://openalex.org/W2972667718","https://openalex.org/W2973216307","https://openalex.org/W3015338123","https://openalex.org/W3094923859","https://openalex.org/W3114898335","https://openalex.org/W3198011653","https://openalex.org/W4238674002","https://openalex.org/W4288079581","https://openalex.org/W4288079605","https://openalex.org/W4288079858","https://openalex.org/W4288079962","https://openalex.org/W4298580827","https://openalex.org/W4390912391"],"related_works":["https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W3163341049","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W2885352820","https://openalex.org/W4296591952"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,27,35,40,64,89,103,115,150,157,166,172],"low-latency":[4],"real-time":[5,158],"(LLRT)":[6],"non-parallel":[7],"voice":[8],"conversion":[9],"(VC)":[10],"framework":[11,92,140],"based":[12],"on":[13,156,165],"cyclic":[14],"variational":[15],"autoencoder":[16],"(CycleVAE)":[17],"and":[18,39,63,73,99,178],"multiband":[19],"WaveRNN":[20],"with":[21,80,85,102,149],"datadriven":[22],"linear":[23],"prediction":[24],"(MWDLP).CycleVAE":[25],"is":[26,60,100],"robust":[28],"nonparallel":[29],"multispeaker":[30,71],"spectral":[31,46,50,97],"model,":[32],"which":[33],"utilizes":[34,94],"speakerindependent":[36],"latent":[37],"space":[38],"speaker-dependent":[41],"code":[42],"to":[43,107],"generate":[44,74],"reconstructed/converted":[45],"features":[47,51,98],"given":[48],"the":[49,56,109,121,127,131,138],"of":[52,152,160,169,175],"an":[53,61],"input":[54],"speaker.On":[55],"other":[57],"hand,":[58],"MWDLP":[59,132],"efficient":[62],"high-quality":[65],"neural":[66],"vocoder":[67],"that":[68,93,119,137],"can":[69],"handle":[70],"data":[72],"speech":[75],"waveform":[76,128],"for":[77,146],"LLRT":[78,83,147],"applications":[79],"CPU.To":[81],"accommodate":[82],"constraint":[84],"CPU,":[86],"we":[87,112],"propose":[88,114],"novel":[90,116],"CycleVAE":[91,123],"mel-spectrogram":[95],"as":[96],"built":[101],"sparse":[104],"network":[105,124],"architecture.Further,":[106],"improve":[108],"modeling":[110],"performance,":[111],"also":[113],"fine-tuning":[117],"procedure":[118],"refines":[120],"frame-rate":[122],"by":[125],"utilizing":[126],"loss":[129],"from":[130],"network.The":[133],"experimental":[134],"results":[135],"demonstrate":[136],"proposed":[139],"achieves":[141],"highperformance":[142],"VC,":[143],"while":[144],"allowing":[145],"usage":[148],"singlecore":[151],"2.1-2.7":[153],"GHz":[154],"CPU":[155],"factor":[159],"0.87-0.95,including":[161],"input/output,":[162],"feature":[163],"extraction,":[164],"frame":[167],"shift":[168],"10":[170],"ms,":[171,177],"window":[173],"length":[174],"27.5":[176],"2":[179],"lookup":[180],"frames.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}