{"id":"https://openalex.org/W4392931291","doi":"https://doi.org/10.1109/icassp48485.2024.10448068","title":"Diversity-Based Core-Set Selection for Text-to-Speech with Linguistic and Acoustic Features","display_name":"Diversity-Based Core-Set Selection for Text-to-Speech with Linguistic and Acoustic Features","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392931291","doi":"https://doi.org/10.1109/icassp48485.2024.10448068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5077904090","display_name":"Kentaro Seki","orcid":"https://orcid.org/0009-0008-2566-2648"},"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":"Kentaro Seki","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"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":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","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":false,"raw_author_name":"Takaaki Saeki","raw_affiliation_strings":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"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":["The University of Tokyo,Japan","The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"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/A5077904090"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73136357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"12351","last_page":"12355"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.8496455550193787},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6818281412124634},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6543617248535156},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6374042630195618},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5106366276741028},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5055251121520996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46834084391593933},{"id":"https://openalex.org/keywords/volume","display_name":"Volume (thermodynamics)","score":0.4598577618598938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4596545100212097},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4575594365596771},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4302639961242676},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41434818506240845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.386345773935318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496455550193787},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6818281412124634},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6543617248535156},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6374042630195618},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5106366276741028},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5055251121520996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46834084391593933},{"id":"https://openalex.org/C20556612","wikidata":"https://www.wikidata.org/wiki/Q4469374","display_name":"Volume (thermodynamics)","level":2,"score":0.4598577618598938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4596545100212097},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4575594365596771},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4302639961242676},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41434818506240845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.386345773935318},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448068","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1583735608","https://openalex.org/W1965255698","https://openalex.org/W1973264045","https://openalex.org/W2152228468","https://openalex.org/W2602144740","https://openalex.org/W2774918944","https://openalex.org/W2788357188","https://openalex.org/W2810011773","https://openalex.org/W2889414197","https://openalex.org/W2890964092","https://openalex.org/W2896457183","https://openalex.org/W2951222872","https://openalex.org/W2964243274","https://openalex.org/W2969049672","https://openalex.org/W2970641574","https://openalex.org/W2972359262","https://openalex.org/W2972950048","https://openalex.org/W3096791609","https://openalex.org/W3134011080","https://openalex.org/W3135644023","https://openalex.org/W3160919572","https://openalex.org/W3198533616","https://openalex.org/W3198694222","https://openalex.org/W4225956675","https://openalex.org/W4226502599","https://openalex.org/W4296068974","https://openalex.org/W4313123884","https://openalex.org/W4372272479","https://openalex.org/W4385823191","https://openalex.org/W6747231328","https://openalex.org/W6748588790","https://openalex.org/W6749555683","https://openalex.org/W6751707208","https://openalex.org/W6767245602","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783867762","https://openalex.org/W6810629572","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,7,11,101,112,119,128,131],"method":[4,102,140],"for":[5,26,50,103],"extracting":[6],"lightweight":[8],"subset":[9,107,129],"from":[10,35,111],"text-to-speech":[12],"(TTS)":[13],"corpus":[14,114,153],"ensuring":[15],"synthetic":[16],"speech":[17],"quality.":[18],"In":[19],"recent":[20],"years,":[21],"methods":[22,45],"have":[23,46],"been":[24],"proposed":[25,139],"constructing":[27],"large-scale":[28],"TTS":[29,56,113],"corpora":[30],"by":[31],"collecting":[32,61],"diverse":[33],"data":[34,65,82,91,148],"massive":[36],"sources":[37],"such":[38],"as":[39,109],"audiobooks":[40],"and":[41,73,152],"YouTube.":[42],"Although":[43],"these":[44,93],"gained":[47],"significant":[48],"attention":[49],"enhancing":[51],"the":[52,80,85,105,116,124,145],"expressive":[53],"capabilities":[54],"of":[55,64,118],"systems,":[57],"they":[58],"often":[59],"prioritize":[60],"vast":[62],"amounts":[63],"without":[66],"considering":[67],"practical":[68],"constraints":[69],"like":[70],"storage":[71],"capacity":[72],"computation":[74],"time":[75],"in":[76],"training,":[77],"which":[78,122,127],"limits":[79],"available":[81],"quantity.":[83],"Consequently,":[84],"need":[86],"arises":[87],"to":[88,126],"efficiently":[89],"collect":[90],"within":[92],"volume":[94],"constraints.":[95],"To":[96],"address":[97],"this,":[98],"we":[99],"propose":[100],"selecting":[104],"core":[106],"(known":[108],"core-set)":[110],"on":[115],"basis":[117],"diversity":[120],"metric,":[121],"measures":[123],"degree":[125],"encompasses":[130],"wide":[132],"range.":[133],"Experimental":[134],"results":[135],"demonstrate":[136],"that":[137],"our":[138],"performs":[141],"significantly":[142],"better":[143],"than":[144],"baseline":[146],"phoneme-balanced":[147],"selection":[149],"across":[150],"language":[151],"size.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
