{"id":"https://openalex.org/W2102042099","doi":"https://doi.org/10.1109/icassp.2011.5947571","title":"Vocal attractiveness of statistical speech synthesisers","display_name":"Vocal attractiveness of statistical speech synthesisers","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2102042099","doi":"https://doi.org/10.1109/icassp.2011.5947571","mag":"2102042099"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/files/15051150/Vocal_attractiveness.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086393503","display_name":"Sandra Andraszewicz","orcid":"https://orcid.org/0000-0001-6958-4962"},"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":"Sandra Andraszewicz","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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 of Speech Technology Research, University of Edinburgh, UK","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"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":"16","issue":null,"first_page":"5368","last_page":"5371"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9991000294685364,"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/speech-recognition","display_name":"Speech recognition","score":0.7869427800178528},{"id":"https://openalex.org/keywords/attractiveness","display_name":"Attractiveness","score":0.6626414656639099},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6161609292030334},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.6092646718025208},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.49701955914497375},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4692803621292114},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4688509404659271},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.433157742023468},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4291347563266754},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.41699278354644775},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23074400424957275}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7869427800178528},{"id":"https://openalex.org/C31173074","wikidata":"https://www.wikidata.org/wiki/Q2632514","display_name":"Attractiveness","level":2,"score":0.6626414656639099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161609292030334},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.6092646718025208},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.49701955914497375},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4692803621292114},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4688509404659271},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.433157742023468},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4291347563266754},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.41699278354644775},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23074400424957275},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5947571","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/65f57b24-fee8-4389-81a4-7816a0f9c326","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/65f57b24-fee8-4389-81a4-7816a0f9c326","pdf_url":"https://www.research.ed.ac.uk/files/15051150/Vocal_attractiveness.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Andraszewicz, S, Yamagishi, J & King, S 2011, Vocal attractiveness of statistical speech synthesisers. in Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. pp. 5368-5371. https://doi.org/10.1109/ICASSP.2011.5947571","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/65f57b24-fee8-4389-81a4-7816a0f9c326","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/65f57b24-fee8-4389-81a4-7816a0f9c326","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15051150/Vocal_attractiveness.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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:era.ed.ac.uk:1842/4863","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4863","pdf_url":null,"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:pure.ed.ac.uk:openaire/65f57b24-fee8-4389-81a4-7816a0f9c326","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/65f57b24-fee8-4389-81a4-7816a0f9c326","pdf_url":"https://www.research.ed.ac.uk/files/15051150/Vocal_attractiveness.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Andraszewicz, S, Yamagishi, J & King, S 2011, Vocal attractiveness of statistical speech synthesisers. in Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on. pp. 5368-5371. https://doi.org/10.1109/ICASSP.2011.5947571","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102042099.pdf","grobid_xml":"https://content.openalex.org/works/W2102042099.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W14154947","https://openalex.org/W1970256373","https://openalex.org/W2042860351","https://openalex.org/W2049686551","https://openalex.org/W2054167181","https://openalex.org/W2064671519","https://openalex.org/W2168411176","https://openalex.org/W2171099065","https://openalex.org/W2309282333","https://openalex.org/W4285719527","https://openalex.org/W6712582474"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2049083033","https://openalex.org/W290673751","https://openalex.org/W2017702615"],"abstract_inverted_index":{"Our":[0,69],"previous":[1],"analysis":[2,61],"of":[3,51,114],"speaker-adaptive":[4],"HMM-based":[5],"speech":[6,33],"synthesis":[7],"methods":[8],"suggested":[9],"that":[10,60,88],"there":[11],"are":[12],"two":[13],"possible":[14],"reasons":[15],"why":[16],"average":[17,77,107],"voices":[18,78,81],"can":[19],"obtain":[20],"higher":[21],"subjective":[22],"scores":[23],"than":[24],"any":[25],"individual":[26],"adapted":[27],"voice:":[28],"1)":[29],"model":[30,83],"adaptation":[31],"degrades":[32],"quality":[34],"proportionally":[35],"to":[36,48,64,92],"the":[37,41,49,52,105,106,110,115,125],"distance":[38,103],"'moved'":[39],"by":[40,99],"transforms,":[42],"and":[43,62,79,86,118],"2)":[44],"psychoacoustic":[45],"effects":[46,67],"relating":[47],"attractiveness":[50],"voice.":[53],"This":[54],"paper":[55],"is":[56,130],"a":[57,94],"follow-on":[58],"from":[59,104],"aims":[63],"separate":[65],"these":[66],"out.":[68],"latest":[70],"perceptual":[71],"experiments":[72],"focus":[73],"on":[74],"attractiveness,":[75],"using":[76,89],"speaker-dependent":[80],"without":[82],"trans":[84],"formation,":[85],"show":[87],"several":[90],"speakers":[91],"create":[93],"voice":[95,108,117],"improves":[96],"smoothness":[97],"(measured":[98],"Harmonics-to-Noise":[100],"Ratio),":[101],"reduces":[102],"in":[109],"log":[111],"F0-F1":[112],"space":[113],"final":[116],"hence":[119],"makes":[120],"it":[121],"more":[122],"attractive":[123],"at":[124,134],"segmental":[126],"level.":[127],"However,":[128],"this":[129],"weakened":[131],"or":[132,136],"overridden":[133],"supra-segmental":[135],"sentence":[137],"levels.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"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"}