{"id":"https://openalex.org/W3007908230","doi":"https://doi.org/10.1109/asru46091.2019.9003801","title":"WaveNet Factorization with Singular Value Decomposition for Voice Conversion","display_name":"WaveNet Factorization with Singular Value Decomposition for Voice Conversion","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007908230","doi":"https://doi.org/10.1109/asru46091.2019.9003801","mag":"3007908230"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003801","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5057476853","display_name":"Hongqiang Du","orcid":"https://orcid.org/0000-0002-4168-9655"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Hongqiang Du","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103156833","display_name":"Xiaohai Tian","orcid":"https://orcid.org/0000-0001-5219-1249"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohai Tian","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, xi'an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5057476853"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.7216,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79786337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"15","issue":null,"first_page":"152","last_page":"159"},"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":0.9988999962806702,"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":0.75096195936203},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.7214728593826294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6707159280776978},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6082029938697815},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5167490839958191},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49968433380126953},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.49241483211517334},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.47961387038230896},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4648849666118622},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4369814693927765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26815783977508545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17512699961662292},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10903385281562805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75096195936203},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.7214728593826294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6707159280776978},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6082029938697815},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5167490839958191},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49968433380126953},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.49241483211517334},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.47961387038230896},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4648849666118622},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4369814693927765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26815783977508545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17512699961662292},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10903385281562805},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru46091.2019.9003801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003801","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"mag:3043009247","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002236860358989","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1497120562","https://openalex.org/W1509691205","https://openalex.org/W1524333225","https://openalex.org/W1977362459","https://openalex.org/W2017425464","https://openalex.org/W2024490156","https://openalex.org/W2057609679","https://openalex.org/W2086796102","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2156142001","https://openalex.org/W2156477760","https://openalex.org/W2169652224","https://openalex.org/W2294543795","https://openalex.org/W2312434537","https://openalex.org/W2471520273","https://openalex.org/W2507580616","https://openalex.org/W2518172956","https://openalex.org/W2519091744","https://openalex.org/W2532494225","https://openalex.org/W2733416080","https://openalex.org/W2746474733","https://openalex.org/W2749651610","https://openalex.org/W2774848319","https://openalex.org/W2803714261","https://openalex.org/W2888867175","https://openalex.org/W2889064624","https://openalex.org/W2889329491","https://openalex.org/W2937579788","https://openalex.org/W2949382160","https://openalex.org/W2954386831","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963971656","https://openalex.org/W2964307104","https://openalex.org/W2972313557","https://openalex.org/W3030286867","https://openalex.org/W4298580827","https://openalex.org/W4299823361","https://openalex.org/W6603838645","https://openalex.org/W6631362777","https://openalex.org/W6696912008","https://openalex.org/W6726528559","https://openalex.org/W6743855016"],"related_works":["https://openalex.org/W2782904003","https://openalex.org/W4226434912","https://openalex.org/W2118633810","https://openalex.org/W2150953077","https://openalex.org/W2002598339","https://openalex.org/W2920931670","https://openalex.org/W2133814741","https://openalex.org/W1995410415","https://openalex.org/W3108343813","https://openalex.org/W4312481107"],"abstract_inverted_index":{"WaveNet":[0,28,39,66,102],"vocoder":[1,40],"has":[2],"seen":[3],"its":[4,70],"great":[5],"advantage":[6],"over":[7],"traditional":[8],"vocoders":[9],"in":[10,53,110],"voice":[11,46,72],"quality.":[12,73],"However,":[13],"it":[14,31],"usually":[15],"requires":[16],"a":[17,26,33,37],"relatively":[18],"large":[19],"amount":[20],"of":[21,112],"speech":[22,49],"data":[23],"to":[24,35,58,64,86],"train":[25],"speaker-dependent":[27],"vocoder.":[29],"Therefore,":[30],"remains":[32],"challenge":[34],"build":[36],"high-quality":[38],"for":[41],"low":[42],"resource":[43],"tasks,":[44],"e.g.":[45],"conversion,":[47],"where":[48],"samples":[50],"are":[51],"limited":[52],"real":[54],"applications.":[55],"We":[56],"propose":[57],"use":[59],"singular":[60],"value":[61],"decomposition":[62],"(SVD)":[63],"reduce":[65],"parameters":[67],"while":[68,117],"maintaining":[69],"output":[71],"Specifically,":[74],"we":[75],"apply":[76],"SVD":[77],"on":[78,92],"dilated":[79],"convolution":[80],"layers,":[81],"and":[82,115],"impose":[83],"semi-orthogonal":[84],"constraint":[85],"improve":[87],"the":[88,100,104],"performance.":[89],"Experiments":[90],"conducted":[91],"CMU-ARCTIC":[93],"database":[94],"show":[95],"that":[96],"as":[97],"compared":[98],"with":[99],"original":[101],"vocoder,":[103],"proposed":[105],"method":[106],"maintains":[107],"similar":[108],"performance,":[109],"terms":[111],"both":[113],"quality":[114],"similarity,":[116],"using":[118],"much":[119],"less":[120],"training":[121],"data.":[122]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}