{"id":"https://openalex.org/W2967220154","doi":"https://doi.org/10.21437/ssw.2019-18","title":"Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs","display_name":"Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2967220154","doi":"https://doi.org/10.21437/ssw.2019-18","mag":"2967220154"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-18","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-18","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052989202","display_name":"Rob Clark","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Rob Clark","raw_affiliation_strings":["Google U.K"],"affiliations":[{"raw_affiliation_string":"Google U.K","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060434979","display_name":"Hanna Sil\u00e9n","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Hanna Silen","raw_affiliation_strings":["Google U.K"],"affiliations":[{"raw_affiliation_string":"Google U.K","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068330105","display_name":"Tom Kenter","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Tom Kenter","raw_affiliation_strings":["Google U.K"],"affiliations":[{"raw_affiliation_string":"Google U.K","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089901093","display_name":"Ralph Leith","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Ralph Leith","raw_affiliation_strings":["Google U.K"],"affiliations":[{"raw_affiliation_string":"Google U.K","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052989202"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210113297"],"apc_list":null,"apc_paid":null,"fwci":1.7341,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88771984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955999851226807,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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/computer-science","display_name":"Computer science","score":0.7060946226119995},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6589717268943787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.5463736653327942},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.541617214679718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4860430359840393},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06009933352470398}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060946226119995},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6589717268943787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5463736653327942},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.541617214679718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4860430359840393},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06009933352470398}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2019-18","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-18","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th ISCA Workshop on Speech Synthesis (SSW 10)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317153","display_name":"DeepMind","ror":"https://ror.org/00971b260"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2093107730","https://openalex.org/W2125700968","https://openalex.org/W2185776260","https://openalex.org/W2277581165","https://openalex.org/W2406225780","https://openalex.org/W2612376646","https://openalex.org/W2748820881","https://openalex.org/W2912293245","https://openalex.org/W2952269766","https://openalex.org/W4294619240"],"related_works":["https://openalex.org/W2789919619","https://openalex.org/W2293457016","https://openalex.org/W3169305685","https://openalex.org/W2351428524","https://openalex.org/W2368779261","https://openalex.org/W1551406738","https://openalex.org/W2610387714","https://openalex.org/W2369308426","https://openalex.org/W1569841287","https://openalex.org/W1512718085"],"abstract_inverted_index":{"Text-to-speech":[0],"systems":[1],"are":[2,36,91,118,157],"typically":[3],"evaluated":[4],"on":[5],"single":[6,122],"sentences.When":[7],"long-form":[8,52,140],"content,":[9],"such":[10],"as":[11,29,77],"data":[12],"consisting":[13],"of":[14,47,51,67,73,125,139,145],"full":[15],"paragraphs":[16,66,127],"or":[17,75],"dialogues":[18],"is":[19,25,38],"considered,":[20],"evaluating":[21,48,60,64,80,146],"sentences":[22,35,61,147],"in":[23,32,62,148],"isolation":[24,149],"not":[26,108,151],"always":[27],"appropriate":[28],"the":[30,34,49,56,81,94,97,137,142],"context":[31,78],"which":[33],"synthesized":[37],"missing.In":[39],"this":[40],"paper,":[41],"we":[42],"investigate":[43],"three":[44,89],"different":[45],"ways":[46],"naturalness":[50],"text-to-speech":[53],"synthesis.We":[54],"compare":[55],"results":[57],"obtained":[58],"from":[59],"isolation,":[63],"whole":[65],"speech,":[68,141],"and":[69,79,102,128,153],"presenting":[70],"a":[71,121,129],"selection":[72],"speech":[74],"text":[76],"subsequent":[82],"speech.We":[83],"find":[84],"that,":[85],"even":[86],"though":[87],"these":[88,105],"evaluations":[90,156],"based":[92],"upon":[93],"same":[95],"material,":[96],"outcomes":[98,106],"differ":[99],"per":[100],"setting,":[101],"moreover":[103],"that":[104,115,134,154],"do":[107],"necessarily":[109],"correlate":[110],"with":[111],"each":[112],"other.We":[113],"show":[114],"our":[116],"findings":[117],"consistent":[119],"between":[120],"speaker":[123],"setting":[124],"read":[126],"two-speaker":[130],"dialogue":[131],"scenario.We":[132],"conclude":[133],"to":[135],"evaluate":[136],"quality":[138],"traditional":[143],"way":[144],"does":[150],"suffice,":[152],"multiple":[155],"required.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}