{"id":"https://openalex.org/W2005104111","doi":"https://doi.org/10.1109/icassp.2010.5495151","title":"Unit selection speech synthesis using multiple speech units at non-adjacent segments for prosody and waveform generation","display_name":"Unit selection speech synthesis using multiple speech units at non-adjacent segments for prosody and waveform generation","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2005104111","doi":"https://doi.org/10.1109/icassp.2010.5495151","mag":"2005104111"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113811305","display_name":"Masatsune Tamura","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatsune Tamura","raw_affiliation_strings":["Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Norbert Braunschweiler","raw_affiliation_strings":["Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","Toshiba Research Europe Limited, Cambridge Research Laboratory, 208 Cambridge Science Park, Milton Road, CB4 0GZ, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge Research Laboratory, Toshiba Research Europe Limited, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, 208 Cambridge Science Park, Milton Road, CB4 0GZ, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001471443","display_name":"Takehiko Kagoshima","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehiko Kagoshima","raw_affiliation_strings":["Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, Kawasaki, Japan","institution_ids":["https://openalex.org/I1292669757"]},{"raw_affiliation_string":"Corporate Research and Development Center, Toshiba Corporation, 1, Komukai-Toshiba-cho, Saiwai-ku, Kawasaki, 212-8582, Japan","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"e88 d","issue":null,"first_page":"4802","last_page":"4805"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9883999824523926,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8450515270233154},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.8389617204666138},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8349124193191528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7329065203666687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7215169668197632},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6144235730171204},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5003519058227539},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45572394132614136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37907126545906067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13297808170318604},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09597000479698181}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8450515270233154},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8389617204666138},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8349124193191528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7329065203666687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215169668197632},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6144235730171204},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5003519058227539},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45572394132614136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37907126545906067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13297808170318604},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09597000479698181},{"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/icassp.2010.5495151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495151","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W33683307","https://openalex.org/W42451021","https://openalex.org/W1972344838","https://openalex.org/W2073541007","https://openalex.org/W2093094447","https://openalex.org/W2150658333","https://openalex.org/W2801578089","https://openalex.org/W3149641078","https://openalex.org/W6601359214","https://openalex.org/W6601724279","https://openalex.org/W6668851075"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W4245668640","https://openalex.org/W1927421023","https://openalex.org/W2388979876","https://openalex.org/W10581632","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W3149582125"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,11,116],"speech":[6,16,41,47,63,68,83,93,103],"synthesis":[7,17],"method":[8,18,34,114,124],"that":[9,58,111],"combines":[10],"natural":[12],"waveform":[13],"concatenation":[14],"based":[15],"and":[19,25,43,89,125],"our":[20,126],"baseline":[21,127],"plural":[22],"unit":[23,69,122],"selection":[24,123],"fusion":[26],"method.":[27,128],"Two":[28],"main":[29],"features":[30],"of":[31,81,91],"the":[32,56,59,66,75,79,85,112,120],"proposed":[33,113],"are":[35,71,94,98],"(i)":[36],"prosody":[37,80],"regeneration":[38],"from":[39],"selected":[40,82],"units":[42,48,64,104],"(ii)":[44],"using":[45,78,101],"multiple":[46,102],"at":[49,105],"non-adjacent":[50,106],"segments.":[51,107],"The":[52],"nonadjacent":[53],"segments":[54],"is":[55],"segment":[57],"previous":[60],"or":[61],"following":[62],"in":[65,74],"optimum":[67],"sequence":[70],"not":[72],"adjacent":[73],"database.":[76],"By":[77],"units,":[84],"original":[86],"prosodic":[87],"expressions":[88],"sounds":[90],"recorded":[92],"retained,":[95],"while":[96],"discontinuities":[97],"reduced":[99],"by":[100],"MOS":[108],"evaluations":[109],"showed":[110],"provides":[115],"clear":[117],"improvement":[118],"against":[119],"conventional":[121]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
