{"id":"https://openalex.org/W2166622886","doi":"https://doi.org/10.1109/icassp.2006.1660162","title":"Constructing a Phonetic-Rich Speech Corpus While Controlling Time-Dependent Voice Quality Variability for English Speech Synthesis","display_name":"Constructing a Phonetic-Rich Speech Corpus While Controlling Time-Dependent Voice Quality Variability for English Speech Synthesis","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2166622886","doi":"https://doi.org/10.1109/icassp.2006.1660162","mag":"2166622886"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5100888269","display_name":"Jinfu Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jinfu Ni","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110129716","display_name":"T. Hirai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Hirai","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"H. Kawai","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","KDD Research and Development Laboratories, Inc., Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"KDD Research and Development Laboratories, Inc., Japan","institution_ids":["https://openalex.org/I4210164495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100888269"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2587,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89607035,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9922000169754028,"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":0.8270694613456726},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6890921592712402},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.6838091015815735},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6058302521705627},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5481855273246765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5406138300895691},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49152812361717224},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4526429772377014},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43353572487831116},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4242079257965088},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41877281665802}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270694613456726},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6890921592712402},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.6838091015815735},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6058302521705627},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5481855273246765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5406138300895691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49152812361717224},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4526429772377014},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43353572487831116},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4242079257965088},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41877281665802},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W197855092","https://openalex.org/W2044992864","https://openalex.org/W2107541077","https://openalex.org/W2110413797","https://openalex.org/W2394921947","https://openalex.org/W6608132974","https://openalex.org/W6712208827"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619","https://openalex.org/W2022789108","https://openalex.org/W2009814707"],"abstract_inverted_index":{"This":[0,16,79],"paper":[1,80],"presents":[2],"a":[3,8,21,87,98,103],"practical":[4],"approach":[5,113],"to":[6,36,52],"constructing":[7],"large-scale":[9],"speech":[10,14],"corpus":[11,24,35,51],"for":[12,90,105,122],"corpus-based":[13],"synthesis.":[15],"consists":[17],"of":[18,62],"(1)":[19],"selecting":[20],"source":[22,33,49],"text":[23,34,50],"that":[25,74],"fits":[26],"limited":[27],"target":[28],"domains;":[29],"(2)":[30],"analyzing":[31],"the":[32,38,48,54,59,93,107,112],"obtain":[37],"unit":[39,56],"statistics;":[40],"(3)":[41],"automatically":[42],"extracting":[43],"prompt":[44,67,91],"subjects":[45,68],"(sentences)":[46],"from":[47],"maximize":[53],"intended":[55],"coverage":[57],"with":[58],"given":[60],"amount":[61],"text;":[63],"and":[64,102],"(4)":[65],"recording":[66,100],"while":[69],"controlling":[70],"such":[71,85],"critical":[72],"factors":[73],"cause":[75],"undesirable":[76],"voice":[77,109],"variability.":[78],"describes":[81],"related":[82],"computational":[83],"methods,":[84],"as":[86],"greedy":[88],"algorithm":[89],"selection,":[92],"proximity":[94],"effects":[95],"found":[96],"in":[97,116],"real":[99],"system,":[101],"technique":[104],"detecting":[106],"timedependent":[108],"variations.":[110],"While":[111],"is":[114,119],"demonstrated":[115],"English,":[117],"it":[118],"also":[120],"promising":[121],"other":[123],"languages.":[124]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}