{"id":"https://openalex.org/W1599623585","doi":"https://doi.org/10.21437/eurospeech.1997-219","title":"Automatically clustering similar units for unit selection in speech synthesis","display_name":"Automatically clustering similar units for unit selection in speech synthesis","publication_year":1997,"publication_date":"1997-09-22","ids":{"openalex":"https://openalex.org/W1599623585","doi":"https://doi.org/10.21437/eurospeech.1997-219","mag":"1599623585"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1997-219","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/1236","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alan W. Black","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089724584","display_name":"Paul Taylor","orcid":"https://orcid.org/0000-0002-8213-0380"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Paul Taylor","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, 80, South Bridge, Edinburgh, U.K. EH1 1HN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, 80, South Bridge, Edinburgh, U.K. EH1 1HN","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5089724584"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":4.9028,"has_fulltext":true,"cited_by_count":284,"citation_normalized_percentile":{"value":0.95699876,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"601","last_page":"604"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9977999925613403,"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":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.762001633644104},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.717925488948822},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6939657330513},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5479259490966797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5329421758651733},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.43495553731918335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41982588171958923},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3714260458946228},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12831902503967285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762001633644104},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.717925488948822},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6939657330513},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5479259490966797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5329421758651733},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.43495553731918335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41982588171958923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3714260458946228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12831902503967285},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/eurospeech.1997-219","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1997-219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th European Conference on Speech Communication and Technology (Eurospeech 1997)","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/1236","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/1236","pdf_url":"http://hdl.handle.net/1842/1236","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.40.4797","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.40.4797","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~awb/papers/ES97units.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.64.446","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.64.446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/1997/Black_1997_b.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.69.472","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.69.472","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~awb/papers/ES97units.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/1236","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/1236","pdf_url":"http://hdl.handle.net/1842/1236","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1599623585.pdf","grobid_xml":"https://content.openalex.org/works/W1599623585.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W64730254","https://openalex.org/W1505932402","https://openalex.org/W1584787447","https://openalex.org/W1594031697","https://openalex.org/W1608375737","https://openalex.org/W2119085432","https://openalex.org/W2150658333","https://openalex.org/W2330820318","https://openalex.org/W3085162807"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2371343292","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W1534720161","https://openalex.org/W2804957450"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,14,48,52,106,131],"new":[4],"method":[5,84,121,127],"for":[6,47],"synthesizing":[7],"speech":[8,139],"by":[9,25,145],"concatenating":[10],"sub-word":[11,148],"units":[12,28,66,149],"from":[13,71],"database":[15],"of":[16,29,55,82,91,147],"labelled":[17],"speech.":[18],"A":[19],"large":[20],"unit":[21,50],"inventory":[22],"is":[23,44,61,115,128],"created":[24],"automatically":[26],"clustering":[27],"the":[30,64,72,83,103,118],"same":[31],"phone":[32],"class":[33],"based":[34,67,78,112],"on":[35,68],"their":[36,69],"phonetic":[37],"and":[38,75,85],"prosodic":[39],"context.":[40],"The":[41,89,126],"appropriate":[42],"cluster":[43,73],"then":[45],"selected":[46],"target":[49],"offering":[51,135],"small":[53],"set":[54],"candidate":[56,65],"units.":[57],"An":[58],"optimal":[59],"path":[60],"found":[62],"through":[63],"distance":[70],"center":[74],"an":[76],"acoustically":[77],"join":[79],"cost.":[80],"Details":[81],"justification":[86],"are":[87,97],"presented.":[88],"results":[90],"experiments":[92],"using":[93],"two":[94],"different":[95],"databases":[96],"given,":[98],"optimising":[99],"various":[100],"parameters":[101],"within":[102,130],"system.":[104],"Also":[105],"comparison":[107],"with":[108],"other":[109],"existing":[110,124],"selection":[111],"synthesis":[113,144],"techniques":[114],"given":[116],"showing":[117],"advantages":[119],"this":[120],"has":[122],"over":[123],"ones.":[125],"implemented":[129],"full":[132],"text-to-speech":[133],"system":[134],"efficient":[136],"natural":[137],"sounding":[138],"synthesis.":[140],"1.":[141],"BACKGROUND":[142],"Speech":[143],"concatenation":[146],"...":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":15}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}
