{"id":"https://openalex.org/W3015710813","doi":"https://doi.org/10.1109/icassp40776.2020.9053047","title":"Transferring Neural Speech Waveform Synthesizers to Musical Instrument Sounds Generation","display_name":"Transferring Neural Speech Waveform Synthesizers to Musical Instrument Sounds Generation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015710813","doi":"https://doi.org/10.1109/icassp40776.2020.9053047","mag":"3015710813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053047","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/A5103063144","display_name":"Yi Zhao","orcid":"https://orcid.org/0000-0002-3555-9408"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081575688","display_name":"Lauri Juvela","orcid":"https://orcid.org/0000-0002-2201-103X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Lauri Juvela","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103063144"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":1.9699,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86576695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6269","last_page":"6273"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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":0.7384731769561768},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7133125066757202},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6275964379310608},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5951334238052368},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5692033767700195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35505127906799316}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384731769561768},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7133125066757202},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6275964379310608},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5951334238052368},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5692033767700195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35505127906799316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053047","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":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W117352590","https://openalex.org/W304834817","https://openalex.org/W1542948701","https://openalex.org/W1994806620","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2584032004","https://openalex.org/W2587284713","https://openalex.org/W2606176153","https://openalex.org/W2749651610","https://openalex.org/W2759171953","https://openalex.org/W2811079561","https://openalex.org/W2898148140","https://openalex.org/W2910577860","https://openalex.org/W2949382160","https://openalex.org/W2950547518","https://openalex.org/W2962721334","https://openalex.org/W2962942158","https://openalex.org/W2962981281","https://openalex.org/W2963139417","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963522141","https://openalex.org/W2963568710","https://openalex.org/W2972309641","https://openalex.org/W2972882294","https://openalex.org/W3101943858","https://openalex.org/W4289761690","https://openalex.org/W6632561901","https://openalex.org/W6732429163","https://openalex.org/W6733471323","https://openalex.org/W6736723571","https://openalex.org/W6752910514","https://openalex.org/W6753018729","https://openalex.org/W6755182157","https://openalex.org/W6758675244","https://openalex.org/W6936113694"],"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/W2039489009","https://openalex.org/W127416991"],"abstract_inverted_index":{"Recent":[0],"neural":[1,59],"waveform":[2,25],"synthesizers":[3,50,60,105],"such":[4],"as":[5],"WaveNet,":[6],"WaveG-low,":[7],"and":[8,31,82,114,151],"the":[9,44,52,79,86,89,101,121,133,137,148],"neural-source-filter":[10],"(NSF)":[11],"model":[12],"have":[13],"shown":[14],"good":[15],"performance":[16,102],"in":[17,41,51,140,147],"speech":[18,30,49,80,87,112,126],"synthesis":[19,34],"despite":[20],"their":[21],"different":[22],"methods":[23],"of":[24,43,94,103,123],"generation.":[26,131],"The":[27,92],"similarity":[28],"between":[29],"music":[32,53,74,90,117,129],"audio":[33,130],"techniques":[35],"suggests":[36],"interesting":[37],"avenues":[38],"to":[39,47,88,159],"explore":[40],"terms":[42],"best":[45,138,146],"way":[46],"apply":[48],"domain.":[54,91],"This":[55],"work":[56],"compares":[57],"three":[58,68,104],"used":[61],"for":[62,128],"musical":[63],"instrument":[64],"sounds":[65],"generation":[66],"under":[67],"scenarios:":[69],"training":[70],"from":[71,78,85,125],"scratch":[72],"on":[73,111,116],"data,":[75,118],"zero-shot":[76,141],"learning":[77,142],"domain,":[81],"fine-tuning-based":[83],"adaptation":[84],"results":[93],"a":[95],"large-scale":[96],"perceptual":[97],"test":[98],"demonstrated":[99],"that":[100,155],"improved":[106],"when":[107],"they":[108],"were":[109,156],"pre-trained":[110],"data":[113,127],"fine-tuned":[115],"which":[119],"indicates":[120],"usefulness":[122],"knowledge":[124],"Among":[132],"synthesizers,":[134],"WaveGlow":[135],"showed":[136],"potential":[139],"while":[143],"NSF":[144],"performed":[145],"other":[149],"scenarios":[150],"could":[152],"generate":[153],"samples":[154],"perceptually":[157],"close":[158],"natural":[160],"audio.":[161]},"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":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}