{"id":"https://openalex.org/W2972484110","doi":"https://doi.org/10.21437/ssw.2019-46","title":"PROMIS: a statistical-parametric speech synthesis system with prominence control via a prominence network","display_name":"PROMIS: a statistical-parametric speech synthesis system with prominence control via a prominence network","publication_year":2019,"publication_date":"2019-09-14","ids":{"openalex":"https://openalex.org/W2972484110","doi":"https://doi.org/10.21437/ssw.2019-46","mag":"2972484110"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2019-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-46","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":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042396987","display_name":"Zofia Malisz","orcid":"https://orcid.org/0000-0001-5953-7310"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zofia Malisz","raw_affiliation_strings":["Department of Speech, Music and Hearing, KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Speech, Music and Hearing, KTH, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052198974","display_name":"Harald Berthelsen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Harald Berthelsen","raw_affiliation_strings":["STTS -S\u00f6dermalms talteknologiservice AB, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"STTS -S\u00f6dermalms talteknologiservice AB, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088064508","display_name":"Jonas Beskow","orcid":"https://orcid.org/0000-0003-1399-6604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonas Beskow","raw_affiliation_strings":["Department of Speech, Music and Hearing, KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Speech, Music and Hearing, KTH, Stockholm, Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["Department of Speech, Music and Hearing, KTH, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Speech, Music and Hearing, KTH, Stockholm, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052198974"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4329,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72194718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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":0.6917408108711243},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6025837659835815},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5568519234657288},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5344362258911133},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5160093307495117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5103678107261658},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4832930862903595},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4539260268211365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3706846833229065},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08733358979225159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917408108711243},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6025837659835815},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5568519234657288},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5344362258911133},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5160093307495117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5103678107261658},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4832930862903595},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4539260268211365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3706846833229065},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08733358979225159},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2019-46","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2019-46","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"},{"id":"pmh:oai:DiVA.org:kth-283137","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283137","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-283137","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-283137","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","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":"","raw_type":"Conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W191179348","https://openalex.org/W197758576","https://openalex.org/W1581480663","https://openalex.org/W1959271118","https://openalex.org/W2032899051","https://openalex.org/W2058673852","https://openalex.org/W2078597717","https://openalex.org/W2130890537","https://openalex.org/W2394962911","https://openalex.org/W2402539796","https://openalex.org/W2428180336","https://openalex.org/W2498127116","https://openalex.org/W2525951546","https://openalex.org/W2598638573","https://openalex.org/W2747252989","https://openalex.org/W2749693600","https://openalex.org/W2752952126","https://openalex.org/W2759925408","https://openalex.org/W2794490148","https://openalex.org/W2884607399","https://openalex.org/W2885189718","https://openalex.org/W2963927338","https://openalex.org/W3080280712","https://openalex.org/W4295731579","https://openalex.org/W4299555621"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250"],"abstract_inverted_index":{"We":[0,19,65],"implement":[1],"an":[2,31],"architecture":[3],"with":[4],"explicit":[5],"prominence":[6,10,35,57,61,77,93,96,99,106,132],"learning":[7],"via":[8],"a":[9,14,76,92,95,108,118],"network":[11,58,68,97],"in":[12,107,136],"Merlin,":[13],"statistical-parametric":[15],"DNN-based":[16],"text-to-speech":[17],"system.":[18],"build":[20],"on":[21,81,122],"our":[22],"previous":[23],"results":[24],"that":[25,59,102],"successfully":[26],"evaluated":[27],"the":[28,38,51,56,67,73,87,130,137],"inclusion":[29],"of":[30,75,111],"automatically":[32],"extracted,":[33],"speech-based":[34],"feature":[36],"into":[37],"training":[39],"and":[40,98],"its":[41],"control":[42,78,138],"at":[43],"synthesis":[44],"time.":[45],"In":[46],"this":[47],"work,":[48],"we":[49],"expand":[50],"PROMIS":[52,89],"system":[53],"by":[54,129],"implementing":[55],"predicts":[60],"values":[62],"from":[63],"text.":[64],"test":[66],"predictions":[69],"as":[70,72],"well":[71],"effects":[74],"module":[79],"based":[80],"SSML-like":[82],"tags.":[83],"Listening":[84],"tests":[85,115],"for":[86],"complete":[88],"system,":[90],"combining":[91],"feature,":[94],"control,":[100],"show":[101,117],"it":[103],"effectively":[104],"controls":[105],"diagnostic":[109],"set":[110],"target":[112],"words.":[113],"The":[114],"also":[116],"minor":[119],"negative":[120],"impact":[121],"perceived":[123],"naturalness,":[124],"relative":[125],"to":[126],"baseline,":[127],"exerted":[128],"two":[131],"tagging":[133],"methods":[134],"implemented":[135],"module.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}