{"id":"https://openalex.org/W4296965655","doi":"https://doi.org/10.21437/interspeech.2022-10132","title":"Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks","display_name":"Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296965655","doi":"https://doi.org/10.21437/interspeech.2022-10132"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10132","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10132","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.11003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","raw_affiliation_strings":["SpeakUnique Ltd., UK","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakUnique Ltd., UK","institution_ids":[]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"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":"Manuel Sam Ribeiro","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["SpeakUnique Ltd., UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SpeakUnique Ltd., UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"471","last_page":"475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9979000091552734,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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/pairwise-comparison","display_name":"Pairwise comparison","score":0.6800028681755066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6692915558815002},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6503256559371948},{"id":"https://openalex.org/keywords/stimulus","display_name":"Stimulus (psychology)","score":0.5867971181869507},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5793748497962952},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5069777965545654},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5043503046035767},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.48019540309906006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4424494504928589},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42496538162231445},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36084309220314026},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36014506220817566},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32416874170303345},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3159672021865845},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.19005650281906128},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15604421496391296},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.12147188186645508}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6800028681755066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692915558815002},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6503256559371948},{"id":"https://openalex.org/C2779918689","wikidata":"https://www.wikidata.org/wiki/Q3771842","display_name":"Stimulus (psychology)","level":2,"score":0.5867971181869507},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5793748497962952},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5069777965545654},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5043503046035767},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.48019540309906006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4424494504928589},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42496538162231445},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36084309220314026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36014506220817566},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32416874170303345},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3159672021865845},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.19005650281906128},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15604421496391296},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.12147188186645508},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2022-10132","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10132","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.11003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11003","pdf_url":"https://arxiv.org/pdf/2209.11003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/bc9701d4-2859-4903-a82f-83fdbf2db358","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/bc9701d4-2859-4903-a82f-83fdbf2db358","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Valentini-Botinhao, C, Ribeiro, M S, Watts, O, Richmond, K & Eje Henter, G 2022, Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks. in H Ko & J H L Hansen (eds), Proceedings of Interspeech 2022. pp. 471-475, Interspeech 2022, Incheon, Korea, Republic of, 18/09/22. https://doi.org/10.21437/Interspeech.2022-10132","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/bc9701d4-2859-4903-a82f-83fdbf2db358","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/bc9701d4-2859-4903-a82f-83fdbf2db358","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.11003","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.11003","pdf_url":"https://arxiv.org/pdf/2209.11003","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W197380572","https://openalex.org/W1120805016","https://openalex.org/W1499332833","https://openalex.org/W1552314771","https://openalex.org/W2067295501","https://openalex.org/W2078597717","https://openalex.org/W2170980774","https://openalex.org/W2277581165","https://openalex.org/W2400063444","https://openalex.org/W2402539796","https://openalex.org/W2403821559","https://openalex.org/W2406990556","https://openalex.org/W2511311723","https://openalex.org/W2557915412","https://openalex.org/W2598638573","https://openalex.org/W2749609415","https://openalex.org/W2767052532","https://openalex.org/W2888804509","https://openalex.org/W2912293245","https://openalex.org/W2963047186","https://openalex.org/W2972394484","https://openalex.org/W2972569067","https://openalex.org/W3024752295","https://openalex.org/W3080280712","https://openalex.org/W3097206152","https://openalex.org/W3097934054","https://openalex.org/W3160506022","https://openalex.org/W4311829866","https://openalex.org/W4385245566","https://openalex.org/W4395962115"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4205262062","https://openalex.org/W2002629668","https://openalex.org/W181477314"],"abstract_inverted_index":{"Automatically":[0],"predicting":[1,32,48],"the":[2,44,56,90,123,129],"outcome":[3],"of":[4,38,47,72,153],"subjective":[5,49],"listening":[6],"tests":[7,113],"is":[8],"a":[9,61,95,103,161],"challenging":[10],"task.":[11],"Ratings":[12],"may":[13],"vary":[14],"from":[15,111,138,151],"person":[16,18],"to":[17,87,114,160,165],"even":[19],"if":[20],"preferences":[21],"are":[22,97],"consistent":[23],"across":[24],"listeners.":[25],"While":[26],"previous":[27],"work":[28],"has":[29],"focused":[30],"on":[31,43,64,70,135],"listeners'":[33,109],"ratings":[34,110],"(mean":[35],"opinion":[36],"scores)":[37],"individual":[39],"stimuli,":[40],"we":[41,107,132],"focus":[42],"simpler":[45],"task":[46],"preference":[50,77],"given":[51],"two":[52],"speech":[53],"stimuli":[54,93],"for":[55,89],"same":[57],"text.":[58],"We":[59,79],"propose":[60],"model":[62,163],"based":[63],"anti-symmetric":[65],"twin":[66],"neural":[67,85],"networks,":[68],"trained":[69,164],"pairs":[71],"waveforms":[73],"and":[74,83],"their":[75],"corresponding":[76],"scores.":[78,168],"explore":[80],"both":[81],"attention":[82],"recurrent":[84],"nets":[86],"account":[88],"fact":[91],"that":[92,116],"in":[94,122],"pair":[96,124],"not":[98],"time":[99],"aligned.":[100],"To":[101],"obtain":[102],"large":[104],"training":[105],"set":[106],"convert":[108],"MUSHRA":[112,140],"values":[115],"reflect":[117],"how":[118],"often":[119],"one":[120],"stimulus":[121],"was":[125],"rated":[126],"higher":[127],"than":[128],"other.":[130],"Specifically,":[131],"evaluate":[133],"performance":[134],"data":[136,152],"obtained":[137],"twelve":[139],"evaluations":[141],"conducted":[142],"over":[143],"five":[144],"years,":[145],"containing":[146],"different":[147,154],"TTS":[148],"systems,":[149],"built":[150],"speakers.":[155],"Our":[156],"results":[157],"compare":[158],"favourably":[159],"state-of-the-art":[162],"predict":[166],"MOS":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}