{"id":"https://openalex.org/W1863665569","doi":"https://doi.org/10.21437/eurospeech.2003-117","title":"Unit selection in concatenative TTS synthesis systems based on mel filter bank amplitudes and phonetic context","display_name":"Unit selection in concatenative TTS synthesis systems based on mel filter bank amplitudes and phonetic context","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1863665569","doi":"https://doi.org/10.21437/eurospeech.2003-117","mag":"1863665569"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5045062178","display_name":"Tanya Lambert","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"T. Lambert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109228866","display_name":"Andrew Breen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew P. Breen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091164340","display_name":"Barry Eggleton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Eggleton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103796951","display_name":"Stephen Cox","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephen J. Cox","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102850641","display_name":"Ben Milner","orcid":"https://orcid.org/0000-0001-6315-3475"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben P. Milner","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045062178"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.468,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72976564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"273","last_page":"276"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9961000084877014,"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":0.9930999875068665,"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/context","display_name":"Context (archaeology)","score":0.7131103873252869},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6871057152748108},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.6690348386764526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6677568554878235},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6176029443740845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6132964491844177},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5079243779182434},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.45530998706817627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31464913487434387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15840622782707214},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.11572054028511047},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10011166334152222}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7131103873252869},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6871057152748108},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6690348386764526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6677568554878235},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6176029443740845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132964491844177},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5079243779182434},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.45530998706817627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31464913487434387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15840622782707214},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.11572054028511047},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10011166334152222},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.2003-117","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.5724","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.5724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2.cmp.uea.ac.uk/~abj/Publications/./Files/ES030983.pdf","raw_type":"text"},{"id":"pmh:oai:ueaeprints.uea.ac.uk:23693","is_oa":false,"landing_page_url":"https://ueaeprints.uea.ac.uk/id/eprint/23693/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400384","display_name":"UEA Digital Repository (University of East Anglia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1118541","host_organization_name":"University of East Anglia","host_organization_lineage":["https://openalex.org/I1118541"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W67398698","https://openalex.org/W1543527380","https://openalex.org/W1560013842","https://openalex.org/W1572730534","https://openalex.org/W1595816827","https://openalex.org/W1927421023","https://openalex.org/W2150658333","https://openalex.org/W2407488922"],"related_works":["https://openalex.org/W2546080374","https://openalex.org/W2017736213","https://openalex.org/W2073052102","https://openalex.org/W2794438528","https://openalex.org/W2611073522","https://openalex.org/W2559071631","https://openalex.org/W2122894838","https://openalex.org/W2107421605","https://openalex.org/W1970615596","https://openalex.org/W2473236733"],"abstract_inverted_index":{"In":[0],"concatenative":[1],"text-to-speech":[2],"(TTS)":[3],"synthesis":[4,31],"systems":[5],"unit":[6,126],"selection":[7,127],"aims":[8],"to":[9,45],"reduce":[10],"the":[11,17,40,65,98,119],"number":[12],"of":[13,32,55,97,103,114,125,132],"concatenation":[14,22,77],"points":[15],"in":[16,95,130],"synthesized":[18],"speech":[19,57,73],"and":[20,47,78,100,108],"make":[21],"joins":[23],"as":[24,26],"smooth":[25],"possible.":[27],"This":[28],"research":[29],"considers":[30],"completely":[33],"new":[34],"utterances":[35],"from":[36,52,70,85],"non-uniform":[37],"units,":[38,43],"whereby":[39],"most":[41,66],"appropriate":[42],"according":[44],"acoustic":[46],"phonetic":[48,101],"criteria,":[49],"are":[50,83,93],"selected":[51],"a":[53,71],"myriad":[54],"similar":[56],"database":[58,68,74],"candidates.":[59],"A":[60],"Viterbi-style":[61],"algorithm":[62],"dynamically":[63],"selects":[64],"suitable":[67],"units":[69],"large":[72],"by":[75],"considering":[76],"target":[79,91],"costs.":[80],"Concatenation":[81],"costs":[82,92],"derived":[84],"mel":[86],"filter":[87],"bank":[88],"amplitudes,":[89],"whereas":[90],"considered":[94],"terms":[96],"phonemic":[99],"properties":[102],"required":[104],"units.":[105],"Within":[106],"subjects":[107,110],"between":[109],"ANOVA":[111],"[9]":[112],"evaluation":[113],"listeners'":[115],"scores":[116],"showed":[117],"that":[118],"TTS":[120],"system":[121],"with":[122],"this":[123],"method":[124],"was":[128],"preferred":[129],"52%":[131],"test":[133],"sentences.":[134]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
