{"id":"https://openalex.org/W3016120005","doi":"https://doi.org/10.1109/icassp40776.2020.9054490","title":"Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials","display_name":"Lifter Training and Sub-Band Modeling for Computationally Efficient and High-Quality Voice Conversion Using Spectral Differentials","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016120005","doi":"https://doi.org/10.1109/icassp40776.2020.9054490","mag":"3016120005"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025983709"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4546,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59414088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"323","issue":null,"first_page":"7784","last_page":"7788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9986000061035156,"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":0.9918000102043152,"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/computer-science","display_name":"Computer science","score":0.6655544638633728},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5903149843215942},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5681930780410767},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.524039089679718},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.5006780624389648},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4740174412727356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37506765127182007},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32271212339401245},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1485762596130371},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10384008288383484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655544638633728},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5903149843215942},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5681930780410767},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.524039089679718},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.5006780624389648},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4740174412727356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37506765127182007},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32271212339401245},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1485762596130371},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10384008288383484},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054490","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054490","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1509691205","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2052871313","https://openalex.org/W2093450784","https://openalex.org/W2118850452","https://openalex.org/W2126143605","https://openalex.org/W2145892079","https://openalex.org/W2170269172","https://openalex.org/W2406654659","https://openalex.org/W2567070169","https://openalex.org/W2749651610","https://openalex.org/W2765486990","https://openalex.org/W2785516183","https://openalex.org/W2794725088","https://openalex.org/W2949117887","https://openalex.org/W2963175743","https://openalex.org/W2963970792","https://openalex.org/W2964121744","https://openalex.org/W2964307104","https://openalex.org/W2969049672","https://openalex.org/W2973216307","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6731370813","https://openalex.org/W6745289305","https://openalex.org/W6748409065","https://openalex.org/W6755610114","https://openalex.org/W6767245602"],"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":{"In":[0],"this":[1,71],"paper,":[2],"we":[3],"propose":[4],"computationally":[5],"efficient":[6],"and":[7,147],"high-quality":[8,31],"methods":[9,62],"for":[10,67,99,132,153],"statistical":[11],"voice":[12],"conversion":[13,32,91],"(VC)":[14],"with":[15,26,119],"direct":[16],"waveform":[17,118],"modification":[18],"based":[19],"on":[20],"spectral":[21],"differentials.":[22],"The":[23],"conventional":[24,102,163],"method":[25,66,72,95,103,131,152],"a":[27,46,56,64,116],"minimum-phase":[28],"filter":[29,74,88],"achieves":[30],"but":[33],"requires":[34],"heavy":[35],"computation":[36],"in":[37,55,78],"filtering.":[38],"This":[39],"is":[40,63,96],"because":[41],"the":[42,50,83,87,101,128,137,144,149,158,162],"minimum":[43],"phase":[44],"using":[45],"fixed":[47],"lifter":[48,68],"of":[49,60,86],"Hilbert":[51],"transform":[52],"often":[53],"results":[54,124],"long-tap":[57],"filter.":[58],"One":[59],"our":[61],"data-driven":[65],"training.":[69],"Since":[70],"takes":[73],"truncation":[75],"into":[76],"account":[77],"training,":[79],"it":[80],"can":[81,114,135,156],"shorten":[82,136],"tap":[84,138],"length":[85,139],"while":[89],"preserving":[90],"accuracy.":[92],"Our":[93],"other":[94],"sub-band":[97],"processing":[98],"extending":[100],"from":[104],"narrow-band":[105,133],"(16":[106],"kHz)":[107,111],"to":[108,140],"full-band":[109,117,154],"(48":[110],"VC,":[112],"which":[113],"convert":[115],"higher":[120],"converted-speech":[121,145,159],"quality.":[122],"Experimental":[123],"indicate":[125],"that":[126],"1)":[127],"proposed":[129,150],"lifter-training":[130],"VC":[134,155],"1/16":[141],"without":[142],"degrading":[143],"quality":[146,160],"2)":[148],"sub-band-processing":[151],"improve":[157],"than":[161],"method.":[164]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}