{"id":"https://openalex.org/W2147623444","doi":"https://doi.org/10.1109/icassp.2008.4518684","title":"Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis","display_name":"Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2147623444","doi":"https://doi.org/10.1109/icassp.2008.4518684","mag":"2147623444"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518684","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5110763152","display_name":"Shinsuke Sakai","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinsuke Sakai","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","National Institute of Information and Communications Technology, Japan","School of informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"School of informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan","School of informatics, Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"School of informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["ATR Spoken Language Communication Research Laboratories, Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Communication Research Laboratories, Japan","institution_ids":[]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7743,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.69827966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4613","last_page":"4616"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.9019496440887451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640526294708252},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7591133117675781},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6769753694534302},{"id":"https://openalex.org/keywords/soft-output-viterbi-algorithm","display_name":"Soft output Viterbi algorithm","score":0.6005542278289795},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.5702245235443115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5312532782554626},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5266668200492859},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.45911189913749695},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4534095525741577},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4117385745048523},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.3167598843574524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2676275670528412},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.20422592759132385},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1774883270263672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1598418951034546},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14622291922569275},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.12741714715957642},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.05323484539985657}],"concepts":[{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.9019496440887451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640526294708252},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7591133117675781},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6769753694534302},{"id":"https://openalex.org/C130319729","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Soft output Viterbi algorithm","level":5,"score":0.6005542278289795},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5702245235443115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5312532782554626},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5266668200492859},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.45911189913749695},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4534095525741577},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4117385745048523},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3167598843574524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2676275670528412},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.20422592759132385},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1774883270263672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1598418951034546},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14622291922569275},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.12741714715957642},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.05323484539985657},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2008.4518684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518684","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.4645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.4645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ar.media.kyoto-u.ac.jp/EN/bib/intl/SAK-ICASSP08.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3629425","https://openalex.org/W91484551","https://openalex.org/W191288280","https://openalex.org/W1577446345","https://openalex.org/W1595816827","https://openalex.org/W2092085867","https://openalex.org/W2099531983","https://openalex.org/W2150658333","https://openalex.org/W2394921947","https://openalex.org/W6603731359","https://openalex.org/W6607729749","https://openalex.org/W6635775141","https://openalex.org/W6674798237","https://openalex.org/W6712208827"],"related_works":["https://openalex.org/W2146383045","https://openalex.org/W2790444905","https://openalex.org/W2143297499","https://openalex.org/W3096277017","https://openalex.org/W4232476001","https://openalex.org/W2099620359","https://openalex.org/W2544568790","https://openalex.org/W3012243213","https://openalex.org/W2783469447","https://openalex.org/W2133857928"],"abstract_inverted_index":{"Corpus-based":[0],"concatenative":[1],"speech":[2,14],"synthesis":[3],"is":[4,26,101,120],"very":[5],"popular":[6],"these":[7],"days":[8],"due":[9],"to":[10],"its":[11,165],"highly":[12],"natural":[13],"quality.":[15],"The":[16,114],"amount":[17,154],"of":[18,77,87,93,97,107,130,148,155],"computation":[19,156],"required":[20,157],"in":[21,53,63,74,122,158],"the":[22,54,64,75,88,91,94,98,108,128,131,136,145,153,159],"run":[23],"time,":[24],"however,":[25],"often":[27],"quite":[28],"large":[29],"and":[30,103],"various":[31],"approaches":[32],"have":[33],"been":[34],"proposed":[35,115,146],"for":[36,49,68,80,117],"reducing":[37],"this":[38,42],"runtime":[39],"computation.":[40],"In":[41],"paper,":[43],"we":[44,59],"propose":[45],"early":[46,62,118],"stopping":[47,119,150],"schemes":[48],"Viterbi":[50,66,132,160],"beam":[51,133,161],"search":[52,134,162],"unit":[55,70],"selection,":[56],"with":[57],"which":[58],"can":[60,111],"stop":[61],"local":[65],"maximization":[67],"each":[69],"as":[71,73],"well":[72],"exploration":[76],"candidate":[78],"units":[79,100],"a":[81],"given":[82],"target.":[83],"It":[84],"takes":[85],"advantage":[86],"fact":[89],"that":[90,123,144],"space":[92],"acoustic":[95],"parameters":[96],"database":[99],"closed":[102],"certain":[104],"upper":[105,137],"bounds":[106,138],"concatenation":[109],"scores":[110],"be":[112],"precomputed.":[113],"method":[116],"admissible":[121,149],"it":[124],"does":[125],"not":[126],"change":[127],"result":[129,166],"if":[135],"are":[139],"properly":[140],"computed.":[141],"Experiments":[142],"show":[143],"methods":[147],"effectively":[151],"reduce":[152],"while":[163],"keeping":[164],"unchanged.":[167]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}