{"id":"https://openalex.org/W2162823987","doi":"https://doi.org/10.21437/interspeech.2010-72","title":"A classifier-based target cost for unit selection speech synthesis trained on perceptual data","display_name":"A classifier-based target cost for unit selection speech synthesis trained on perceptual data","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2162823987","doi":"https://doi.org/10.21437/interspeech.2010-72","mag":"2162823987"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-72","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-72","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/4643","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028468680","display_name":"Volker Strom","orcid":null},"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":"Volker Strom","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028468680"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"153"},"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":0.9994000196456909,"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":0.996999979019165,"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/classifier","display_name":"Classifier (UML)","score":0.8058514595031738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805395126342773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5748010873794556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.571103572845459},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.528016984462738},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42775338888168335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39654961228370667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37692320346832275},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07648122310638428}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.8058514595031738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805395126342773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748010873794556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.571103572845459},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.528016984462738},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42775338888168335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39654961228370667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37692320346832275},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07648122310638428},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2010-72","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-72","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/4643","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4643","pdf_url":"http://hdl.handle.net/1842/4643","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:pure.ed.ac.uk:publications/eaed87f0-b3a8-486a-b7b8-9d0ff14cf8e2","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/eaed87f0-b3a8-486a-b7b8-9d0ff14cf8e2","pdf_url":"https://www.pure.ed.ac.uk/ws/files/8425552/A_classifier_based_target_cost_for_unit_selection_speech_synthesis_trained_on_perceptual_data.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.4157","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.4157","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/2010/strom10d.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/eaed87f0-b3a8-486a-b7b8-9d0ff14cf8e2","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eaed87f0-b3a8-486a-b7b8-9d0ff14cf8e2","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Strom, V & King, S 2010, A Classifier-based target cost for unit selection speech synthesis trained on perceptual data. in Proc. Interspeech.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/4643","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4643","pdf_url":"http://hdl.handle.net/1842/4643","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":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7725608835","display_name":"Automatic target cost and database design for unit-selection speech synthesis","funder_award_id":"EP/E031447/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"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/W2162823987.pdf","grobid_xml":"https://content.openalex.org/works/W2162823987.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W42179106","https://openalex.org/W97174977","https://openalex.org/W1493093888","https://openalex.org/W1912941063","https://openalex.org/W2150658333","https://openalex.org/W2735905505"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W3203087560","https://openalex.org/W4361279463","https://openalex.org/W2216757598","https://openalex.org/W2961085424","https://openalex.org/W105296515","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W234770729","https://openalex.org/W4387697615"],"abstract_inverted_index":{"Our":[0],"goal":[1],"is":[2,22,39,182],"to":[3,23,41,49,56,99],"automatically":[4,175],"learn":[5],"a":[6,12,25,43,51,112,133],"perceptually-optimal":[7],"target":[8,70,128,151,156,169,191,199],"cost":[9,71,83,129,152,157,200],"function":[10],"for":[11,105,114],"unit":[13,197],"selection":[14],"speech":[15,195],"synthesiser.":[16],"The":[17,34],"approach":[18],"we":[19,62,110,131],"take":[20],"here":[21],"train":[24],"classifier":[26,38,134],"on":[27,135,159],"human":[28,137],"perceptual":[29,60,138,180],"judgements":[30],"of":[31,36,144,179],"synthetic":[32],"speech.":[33],"output":[35],"the":[37,58,68,76,81,88,92,120,154,160,167],"used":[40],"make":[42],"simple":[44],"three-way":[45],"distinction":[46],"rather":[47],"than":[48],"estimate":[50],"continuously-valued":[52],"cost.":[53,192],"In":[54],"order":[55],"collect":[57],"necessary":[59],"data,":[61,181],"synthesised":[63,141],"145,137":[64],"short":[65],"sentences":[66,90,146],"with":[67,91,147],"usual":[69],"switched":[72],"off,":[73],"so":[74],"that":[75,166],"search":[77],"was":[78,172],"driven":[79],"by":[80],"join":[82],"only.":[84],"We":[85,140],"then":[86],"selected":[87],"7200":[89],"best":[93],"joins":[94],"and":[95,153],"asked":[96],"60":[97],"listeners":[98],"judge":[100],"them,":[101],"providing":[102],"their":[103],"ratings":[104],"each":[106,115],"syllable.":[107],"From":[108],"this,":[109],"derived":[111],"rating":[113],"demiphone.":[116],"Using":[117],"as":[118,184,186],"input":[119],"same":[121],"context":[122],"features":[123],"employed":[124],"in":[125],"our":[126,149,187],"conventional":[127],"function,":[130],"trained":[132],"these":[136],"ratings.":[139],"two":[142],"sets":[143],"test":[145],"both":[148],"standard":[150,190],"new":[155],"based":[158],"classifier.":[161],"A/B":[162],"preference":[163],"tests":[164],"showed":[165],"classifier-based":[168],"cost,":[170],"which":[171],"learned":[173],"completely":[174],"from":[176],"modest":[177],"amounts":[178],"almost":[183],"good":[185],"carefullyand":[188],"expertly-tuned":[189],"Index":[193],"Terms:":[194],"synthesis,":[196],"selection,":[198],"1.":[201]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
