{"id":"https://openalex.org/W2146873930","doi":"https://doi.org/10.1109/icassp.2003.1198875","title":"A method of unit preselection for speech synthesis based on acoustic clustering and decision trees","display_name":"A method of unit preselection for speech synthesis based on acoustic clustering and decision trees","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2146873930","doi":"https://doi.org/10.1109/icassp.2003.1198875","mag":"2146873930"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198875","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5054585121","display_name":"Christian Blouin","orcid":"https://orcid.org/0000-0002-4434-4142"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"C. Blouin","raw_affiliation_strings":["France Telecom R&D, Lannion, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"France Telecom R&D, Lannion, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020207668","display_name":"Paul C. Bagshaw","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"P.C. Bagshaw","raw_affiliation_strings":["France Telecom R&D, Lannion, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"France Telecom R&D, Lannion, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046789266","display_name":"Olivier Rosec","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"O. Rosec","raw_affiliation_strings":["France Telecom R&D, Lannion, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"France Telecom R&D, Lannion, France","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":0.5108,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65476841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"692"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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":0.9950000047683716,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6952309608459473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6895661354064941},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6535379886627197},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5574989914894104},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5423638820648193},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.476937472820282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30428066849708557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15416297316551208}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6952309608459473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6895661354064941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6535379886627197},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5574989914894104},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5423638820648193},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.476937472820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30428066849708557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15416297316551208},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198875","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W60941773","https://openalex.org/W1560013842","https://openalex.org/W1599623585","https://openalex.org/W1992419399","https://openalex.org/W2116669443","https://openalex.org/W2125055259","https://openalex.org/W2128160875","https://openalex.org/W2330820318","https://openalex.org/W2404901654","https://openalex.org/W3085162807","https://openalex.org/W6602482793","https://openalex.org/W6713620858"],"related_works":["https://openalex.org/W611386996","https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2132641928","https://openalex.org/W2090259340","https://openalex.org/W4310225030","https://openalex.org/W2371343292","https://openalex.org/W2083665254","https://openalex.org/W2393816671","https://openalex.org/W1534720161"],"abstract_inverted_index":{"The":[0,12,64,91],"article":[1],"presents":[2],"a":[3,17,27,44,99,103],"method":[4,13,93,101],"to":[5,52,84,98],"preselect":[6],"units":[7,50,65],"for":[8,30,43,60],"concatenative":[9],"speech":[10],"synthesis.":[11],"is":[14,24,77,94],"based":[15],"on":[16],"procedure":[18],"of":[19,33,87],"unsupervised":[20],"acoustic":[21,41],"clustering":[22],"that":[23],"coupled":[25],"with":[26],"decision":[28],"tree":[29],"each":[31],"type":[32,86],"unit.":[34],"During":[35],"synthesis,":[36],"the":[37,40,49,53,61,75],"trees":[38],"predict":[39],"classes":[42,55],"given":[45],"symbolic":[46],"target":[47],"and":[48,72,80],"belonging":[51],"predicted":[54],"are":[56,70],"retained":[57],"as":[58],"candidates":[59],"final":[62],"selection.":[63],"used":[66],"in":[67,102],"this":[68],"study":[69],"phones":[71],"diphones,":[73],"although":[74],"methodology":[76],"entirely":[78],"automatic":[79],"may":[81],"be":[82],"applied":[83],"any":[85],"unit":[88],"or":[89],"language.":[90],"proposed":[92],"evaluated":[95],"by":[96],"comparison":[97],"handcrafted":[100],"formal":[104],"listening":[105],"test.":[106]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}