{"id":"https://openalex.org/W1493929315","doi":"https://doi.org/10.21437/eurospeech.2003-122","title":"Kalman-filter based join cost for unit-selection speech synthesis","display_name":"Kalman-filter based join cost for unit-selection speech synthesis","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1493929315","doi":"https://doi.org/10.21437/eurospeech.2003-122","mag":"1493929315"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-122","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-122","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/1118","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106182403","display_name":"Jithendra Vepa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jithendra Vepa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7876,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.84853299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"296"},"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":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9966999888420105,"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":0.705826997756958},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.6757280230522156},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6720463037490845},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.561010479927063},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5404402613639832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180411338806152},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4139585494995117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3031645715236664},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12476900219917297}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705826997756958},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.6757280230522156},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6720463037490845},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.561010479927063},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5404402613639832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180411338806152},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4139585494995117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3031645715236664},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12476900219917297},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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":2,"locations":[{"id":"doi:10.21437/eurospeech.2003-122","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-122","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:era.ed.ac.uk:1842/1118","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/eurospeech_2003","pdf_url":"http://hdl.handle.net/1842/1118","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"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/1118","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/eurospeech_2003","pdf_url":"http://hdl.handle.net/1842/1118","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1493929315.pdf","grobid_xml":"https://content.openalex.org/works/W1493929315.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W60941773","https://openalex.org/W116305788","https://openalex.org/W1549321558","https://openalex.org/W1561506132","https://openalex.org/W1626341607","https://openalex.org/W1733696394","https://openalex.org/W1809686770","https://openalex.org/W1887401733","https://openalex.org/W1953513750","https://openalex.org/W2149361029","https://openalex.org/W2150658333","https://openalex.org/W2155797931"],"related_works":["https://openalex.org/W3214148052","https://openalex.org/W2151692181","https://openalex.org/W4248476017","https://openalex.org/W2515443718","https://openalex.org/W794462722","https://openalex.org/W2807741550","https://openalex.org/W1525319740","https://openalex.org/W4247864646","https://openalex.org/W1484210779","https://openalex.org/W2348275208"],"abstract_inverted_index":{"We":[0,87],"introduce":[1],"a":[2,15,22,99,106],"new":[3],"method":[4],"for":[5,52],"computing":[6],"join":[7,70,74],"cost":[8,75],"in":[9,37],"unit-selection":[10,109],"speech":[11,68],"synthesis":[12],"which":[13,38],"uses":[14,33],"linear":[16],"dynamical":[17],"model":[18,26,32,59,82],"(also":[19],"known":[20],"as":[21,49],"Kalman":[23],"filter)":[24],"to":[25,63],"line":[27],"spectral":[28],"frequency":[29],"trajectories.":[30,43],"The":[31,72],"an":[34,50],"underlying":[35,53],"subspace":[36,45],"it":[39],"makes":[40],"smooth,":[41],"continuous":[42],"This":[44],"can":[46,60],"be":[47,61],"seen":[48],"analogy":[51],"articulator":[54],"movement.":[55],"Once":[56],"trained,":[57],"the":[58,79],"used":[62],"measure":[64,92],"how":[65],"well":[66],"concatenated":[67],"segments":[69],"together.":[71],"objective":[73],"is":[76],"based":[77],"on":[78],"error":[80],"between":[81,90],"predictions":[83],"and":[84,93],"actual":[85],"observations.":[86],"report":[88],"correlations":[89],"this":[91],"mean":[94],"listener":[95],"scores":[96],"obtained":[97],"from":[98,113],"perceptual":[100],"listening":[101],"experiment.":[102],"Our":[103],"experiments":[104],"use":[105],"state-of-the":[107],"art":[108],"text-to-speech":[110],"system:":[111],"`rVoice'":[112],"Rhetorical":[114],"Systems":[115],"Ltd.":[116]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}