{"id":"https://openalex.org/W3007264682","doi":"https://doi.org/10.21437/odyssey.2020-32","title":"Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis","display_name":"Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis","publication_year":2020,"publication_date":"2020-05-15","ids":{"openalex":"https://openalex.org/W3007264682","doi":"https://doi.org/10.21437/odyssey.2020-32","mag":"3007264682"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2020-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2002.12645","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040626187","display_name":"Jennifer Williams","orcid":"https://orcid.org/0000-0003-1410-0427"},"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":"Jennifer Williams","raw_affiliation_strings":["University of Edinburgh,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026578899","display_name":"Joanna Rownicka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joanna Rownicka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045684390","display_name":"Pilar Oplustil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pilar Oplustil","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"229"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9955000281333923,"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/spectrogram","display_name":"Spectrogram","score":0.7738258242607117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695969343185425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613025307655334},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.6641975045204163},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5985990762710571},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5629101395606995},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5533596277236938},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5132696628570557},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5099953413009644},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.49212974309921265},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4700915813446045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44295910000801086},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43752026557922363},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3255837857723236},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1025354266166687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10141322016716003}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7738258242607117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695969343185425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613025307655334},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.6641975045204163},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5985990762710571},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5629101395606995},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5533596277236938},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5132696628570557},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5099953413009644},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.49212974309921265},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4700915813446045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44295910000801086},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43752026557922363},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3255837857723236},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1025354266166687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10141322016716003},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/odyssey.2020-32","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2020-32","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2020)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2002.12645","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.12645","pdf_url":"https://arxiv.org/pdf/2002.12645","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"mag:3007264682","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2002.12645.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:eprints.soton.ac.uk:470319","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/470319/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"doi:10.48550/arxiv.2002.12645","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2002.12645","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2002.12645","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.12645","pdf_url":"https://arxiv.org/pdf/2002.12645","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[{"id":"https://openalex.org/G4437068315","display_name":"EPSRC Centre for Doctoral Training in Data Science","funder_award_id":"EP/L016427/1","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"},{"id":"https://openalex.org/F4320334812","display_name":"Comisi\u00f3n Nacional de Investigaci\u00f3n Cient\u00edfica y Tecnol\u00f3gica","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3007264682.pdf","grobid_xml":"https://content.openalex.org/works/W3007264682.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1572063013","https://openalex.org/W2004915807","https://openalex.org/W2025440555","https://openalex.org/W2048957655","https://openalex.org/W2153773386","https://openalex.org/W2402144811","https://openalex.org/W2557915412","https://openalex.org/W2746419079","https://openalex.org/W2765860599","https://openalex.org/W2767052532","https://openalex.org/W2791686384","https://openalex.org/W2890964092","https://openalex.org/W2937993361","https://openalex.org/W2950924994","https://openalex.org/W2963403924","https://openalex.org/W2972419867","https://openalex.org/W2972569067","https://openalex.org/W2973143722","https://openalex.org/W2989031006","https://openalex.org/W3007327651","https://openalex.org/W3011535310","https://openalex.org/W3039270522"],"related_works":["https://openalex.org/W3205133942","https://openalex.org/W3207961486","https://openalex.org/W3107262928","https://openalex.org/W1547848553","https://openalex.org/W3195366621","https://openalex.org/W2890301597","https://openalex.org/W2571786242","https://openalex.org/W299254312","https://openalex.org/W1996716433","https://openalex.org/W2127684947","https://openalex.org/W2467310271","https://openalex.org/W2768833706","https://openalex.org/W2914049472","https://openalex.org/W1553381619","https://openalex.org/W151271698","https://openalex.org/W3146104336","https://openalex.org/W178451538","https://openalex.org/W2465492956","https://openalex.org/W2102042099","https://openalex.org/W2883691078"],"abstract_inverted_index":{"We":[0,18,117],"aim":[1],"to":[2,8,70,114,165,170,204],"characterize":[3],"how":[4,68],"different":[5,48,79,97],"speakers":[6,132,148],"contribute":[7],"the":[9,21,56,127,137],"perceived":[10],"output":[11],"quality":[12,22,128,151,174,180],"of":[13,23,99,136],"multi-speaker":[14,188],"Text-to-Speech":[15],"(TTS)":[16],"synthesis.":[17],"automatically":[19],"rate":[20],"TTS":[24,49,138,157,189],"using":[25,185],"a":[26,111,156,186],"neural":[27],"network":[28],"(NN)":[29],"trained":[30,193],"on":[31,46,194],"human":[32,115,206],"mean":[33],"opinion":[34],"score":[35],"(MOS)":[36],"ratings.":[37],"First,":[38],"we":[39,76,178],"train":[40],"and":[41,50,91,121,197],"evaluate":[42],"our":[43,159,173,199,209],"NN":[44,107,210],"model":[45,96],"13":[47],"voice":[51],"conversion":[52],"(VC)":[53],"systems":[54],"from":[55],"ASVSpoof":[57],"2019":[58],"Logical":[59],"Access":[60],"(LA)":[61],"Dataset.":[62],"Since":[63],"it":[64],"is":[65,126,143],"not":[66],"known":[67],"best":[69],"represent":[71],"speech":[72,184],"for":[73,130,154,182],"this":[74],"task,":[75],"compare":[77,205],"8":[78],"representations":[80,86],"alongside":[81],"MOSNet":[82],"frame-based":[83],"features.":[84],"Our":[85,106],"include":[87],"image-based":[88],"spectrogram":[89],"features":[90],"x-vector":[92],"embeddings":[93],"that":[94,146,191],"explicitly":[95],"types":[98],"noise":[100],"such":[101,167],"as":[102],"T60":[103],"reverberation":[104],"time.":[105],"predicts":[108],"MOS":[109,201],"with":[110,208],"high":[112],"correlation":[113,120],"judgments.":[116],"report":[118],"prediction":[119,175],"error.":[122],"A":[123],"key":[124],"finding":[125],"achieved":[129],"certain":[131],"seems":[133],"consistent,":[134],"regardless":[135],"or":[139],"VC":[140],"system.":[141],"It":[142],"widely":[144],"accepted":[145],"some":[147],"give":[149],"higher":[150],"than":[152],"others":[153],"building":[155],"system:":[158],"method":[160],"provides":[161],"an":[162],"automatic":[163],"way":[164],"identify":[166],"speakers.":[168],"Finally,":[169],"see":[171],"if":[172],"models":[176],"generalize,":[177],"predict":[179],"scores":[181],"synthetic":[183],"separate":[187],"system":[190],"was":[192],"LibriTTS":[195],"data,":[196],"conduct":[198],"own":[200],"listening":[202],"test":[203],"ratings":[207],"predictions.":[211]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}