{"id":"https://openalex.org/W2121712227","doi":"https://doi.org/10.21437/interspeech.2004-441","title":"Subjective evaluation of join cost functions used in unit selection speech synthesis","display_name":"Subjective evaluation of join cost functions used in unit selection speech synthesis","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W2121712227","doi":"https://doi.org/10.21437/interspeech.2004-441","mag":"2121712227"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/934","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":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1181","last_page":"1184"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.9659237861633301},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7110887169837952},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6545814871788025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5996096730232239},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5573968887329102},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.5508133769035339},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5417552590370178},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47925400733947754},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42037859559059143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3527069687843323},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35089001059532166},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.32383811473846436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17832928895950317},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07405897974967957},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.07343986630439758}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.9659237861633301},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110887169837952},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6545814871788025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5996096730232239},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5573968887329102},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.5508133769035339},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5417552590370178},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47925400733947754},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42037859559059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3527069687843323},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35089001059532166},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.32383811473846436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17832928895950317},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07405897974967957},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07343986630439758},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2004-441","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/934","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/934","pdf_url":"http://hdl.handle.net/1842/934","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:infoscience.tind.io:83064","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/228491","pdf_url":"http://infoscience.epfl.ch/record/83064","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"report"},{"id":"pmh:oai:infoscience.tind.io:83115","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83115","pdf_url":"https://infoscience.epfl.ch/record/83115/files/rr04-26.pdf","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"http://infoscience.epfl.ch/record/83115","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:83064","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/83064","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/934","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/934","pdf_url":"http://hdl.handle.net/1842/934","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2121712227.pdf"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1493929315","https://openalex.org/W1733696394","https://openalex.org/W1809686770","https://openalex.org/W2068804781","https://openalex.org/W2150658333","https://openalex.org/W4255275520","https://openalex.org/W4285719527","https://openalex.org/W4302060808"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W15468680"],"abstract_inverted_index":{"In":[0,73],"our":[1],"previous":[2],"papers,":[3],"we":[4,37,76],"have":[5,15,38],"proposed":[6],"join":[7,85],"cost":[8,86],"functions":[9],"derived":[10],"from":[11,61,69],"spectral":[12,43],"distances,":[13],"which":[14],"good":[16],"correlations":[17],"with":[18],"perceptual":[19],"scores":[20],"obtained":[21,60],"for":[22,56,80],"a":[23,50,62],"range":[24],"of":[25,82],"concatenation":[26,35],"discontinuities.":[27],"To":[28],"further":[29],"validate":[30],"their":[31],"ability":[32],"to":[33],"predict":[34],"discontinuities,":[36],"chosen":[39],"the":[40,83],"best":[41],"three":[42,84],"distances":[44],"and":[45],"evaluated":[46],"them":[47],"subjectively":[48],"in":[49],"listening":[51],"test.":[52],"The":[53],"unit":[54,64],"sequences":[55],"synthesis":[57],"stimuli":[58],"are":[59],"state-of-the-art":[63],"selection":[65],"text-to-speech":[66],"system:":[67],"rVoice":[68],"Rhetorical":[70],"Systems":[71],"Ltd.":[72],"this":[74],"paper,":[75],"report":[77],"listeners'":[78],"preferences":[79],"each":[81],"functions.":[87]},"counts_by_year":[{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
