{"id":"https://openalex.org/W3197461241","doi":"https://doi.org/10.21437/interspeech.2021-806","title":"Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder","display_name":"Relational Data Selection for Data Augmentation of Speaker-Dependent Multi-Band MelGAN Vocoder","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197461241","doi":"https://doi.org/10.21437/interspeech.2021-806","mag":"3197461241"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-806","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"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":"Yi-Chiao Wu","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071175201","display_name":"Cheng-Hung Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Hung Hu","raw_affiliation_strings":["Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066130866","display_name":"Yuhuai Peng","orcid":"https://orcid.org/0000-0001-9343-5377"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Huai Peng","raw_affiliation_strings":["Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000377034","display_name":"Wen-Chin Huang","orcid":"https://orcid.org/0000-0003-3172-3335"},"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":"Wen-Chin Huang","raw_affiliation_strings":["Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"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":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5604757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3630","last_page":"3634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9980999827384949,"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":0.8413745760917664},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6798856258392334},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5592846274375916},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.506362795829773},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47611838579177856},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.446600079536438},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.44474494457244873},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4300232231616974},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39042750000953674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413745760917664},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6798856258392334},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5592846274375916},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.506362795829773},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47611838579177856},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.446600079536438},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.44474494457244873},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4300232231616974},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39042750000953674},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-806","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-806","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/4"}],"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/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","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":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1589137271","https://openalex.org/W2049686551","https://openalex.org/W2121812409","https://openalex.org/W2164764235","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2801291345","https://openalex.org/W2810457573","https://openalex.org/W2811096537","https://openalex.org/W2890964092","https://openalex.org/W2912237252","https://openalex.org/W2939051810","https://openalex.org/W2954386831","https://openalex.org/W2963300588","https://openalex.org/W2963796886","https://openalex.org/W2963840672","https://openalex.org/W2963975282","https://openalex.org/W2964161387","https://openalex.org/W2970006822","https://openalex.org/W2971753973","https://openalex.org/W2973190269","https://openalex.org/W2996286887","https://openalex.org/W3008480565","https://openalex.org/W3015338123","https://openalex.org/W3094402293","https://openalex.org/W3162794600","https://openalex.org/W4289305009","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Nowadays,":[0],"neural":[1],"vocoders":[2],"can":[3],"generate":[4],"very":[5],"high-fidelity":[6],"speech":[7],"when":[8],"a":[9,16,22,31,37,52],"bunch":[10],"of":[11,34,36,48,63,129],"training":[12],"data":[13,35,53,98,122],"is":[14,27,66],"available.Although":[15],"speaker-dependent":[17],"(SD)":[18],"vocoder":[19,101,110,118],"usually":[20],"outperforms":[21],"speaker-independent":[23],"(SI)":[24],"vocoder,":[25],"it":[26],"impractical":[28],"to":[29,80],"collect":[30],"large":[32],"amount":[33],"specific":[38],"target":[39,50,82,97,115],"speaker":[40,58,64,78,83],"for":[41,99],"most":[42],"realworld":[43],"applications.To":[44],"tackle":[45],"the":[46,81,91,95,109,117,125],"problem":[47],"limited":[49,96,114],"data,":[51,116],"augmentation":[54],"method":[55,72],"based":[56],"on":[57],"representation":[59],"and":[60,88,127],"similarity":[61,128],"measurement":[62],"verification":[65],"proposed":[67,71],"in":[68],"this":[69],"paper.The":[70],"selects":[73],"utterances":[74,93],"that":[75],"have":[76],"similar":[77],"identity":[79],"from":[84],"an":[85],"external":[86],"corpus,":[87],"then":[89],"combines":[90],"selected":[92],"with":[94,108],"SD":[100],"adaptation.The":[102],"evaluation":[103],"results":[104],"show":[105],"that,":[106],"compared":[107],"adapted":[111,119],"using":[112,120],"only":[113],"augmented":[121],"improves":[123],"both":[124],"quality":[126],"synthesized":[130],"speech.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
