{"id":"https://openalex.org/W4391021539","doi":"https://doi.org/10.1109/asru57964.2023.10389773","title":"Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech","display_name":"Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021539","doi":"https://doi.org/10.1109/asru57964.2023.10389773"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389773","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/en/publications/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075338116","display_name":"Nicholas Sanders","orcid":"https://orcid.org/0000-0003-1807-5652"},"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":"Nicholas Sanders","raw_affiliation_strings":["University of Edinburgh,The Centre for Speech Technology Research","The Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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":["University of Edinburgh,The Centre for Speech Technology Research","The Centre for Speech Technology Research, University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"157","issue":null,"first_page":"1","last_page":"7"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/focus","display_name":"Focus (optics)","score":0.8009518384933472},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7780759334564209},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6606401205062866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6386513113975525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5877915024757385},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5393175482749939},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5366055369377136},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4338997006416321},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.42169857025146484},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17374229431152344}],"concepts":[{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.8009518384933472},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7780759334564209},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6606401205062866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6386513113975525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5877915024757385},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5393175482749939},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5366055369377136},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4338997006416321},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42169857025146484},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17374229431152344},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru57964.2023.10389773","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Sanders, N & Richmond, K 2024, Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech. in 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)., 10389773, Institute of Electrical and Electronics Engineers, pp. 1-7, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 16/12/23. https://doi.org/10.1109/ASRU57964.2023.10389773","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/408558889/ASRU_2023_Submission-4.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Sanders, N & Richmond, K 2024, Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech. in 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)., 10389773, Institute of Electrical and Electronics Engineers, pp. 1-7, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 16/12/23. https://doi.org/10.1109/ASRU57964.2023.10389773","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/61363cf4-0a6a-46b8-b46f-da4bfa7baeeb","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"Sanders, N & Richmond, K 2024, Invert-Classify: Recovering Discrete Prosody Inputs for Text-To-Speech. in 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)., 10389773, Institute of Electrical and Electronics Engineers, pp. 1-7, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 16/12/23. https://doi.org/10.1109/ASRU57964.2023.10389773","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2077437848","https://openalex.org/W2081539155","https://openalex.org/W2747874407","https://openalex.org/W2918595871","https://openalex.org/W2964138190","https://openalex.org/W2996573371","https://openalex.org/W3092028330","https://openalex.org/W3097003111","https://openalex.org/W3150572638","https://openalex.org/W3198311967","https://openalex.org/W3214634826","https://openalex.org/W4313679638","https://openalex.org/W6631190155","https://openalex.org/W6749555683","https://openalex.org/W6762287338","https://openalex.org/W6768443183","https://openalex.org/W6783867762","https://openalex.org/W6790138166","https://openalex.org/W6841755765","https://openalex.org/W6848735303"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2355553914","https://openalex.org/W2358755282","https://openalex.org/W149862513","https://openalex.org/W2347684782","https://openalex.org/W2054460271"],"abstract_inverted_index":{"Modeling":[0,42],"prosody":[1],"in":[2,49,60],"Text-to-Speech":[3],"(TTS)":[4],"is":[5],"challenging":[6],"due":[7],"to":[8,33,36,87,101],"ambiguous":[9],"orthography":[10],"and":[11,82,139],"the":[12,23,28,57,66,73],"high":[13],"cost":[14],"of":[15,25,30,43,68,99,112],"annotating":[16],"prosodic":[17],"events.":[18],"This":[19],"study":[20],"focuses":[21],"on":[22,123],"modeling":[24],"contrastive":[26,44,90,104,141],"focus,":[27],"emphasis":[29],"a":[31,61,78,96],"word":[32,58],"contrast":[34],"it":[35],"presuppositions":[37],"held":[38],"by":[39,51],"an":[40],"interlocutor.":[41],"focus":[45,91,105],"can":[46],"be":[47],"done":[48],"TTS":[50,80],"using":[52],"binary,":[53],"symbolic":[54],"inputs":[55],"at":[56],"level":[59],"supervised":[62],"setting.":[63],"To":[64],"address":[65],"absence":[67],"annotated":[69,113],"data,":[70],"we":[71],"propose":[72],"Invert-Classify":[74,128],"method,":[75],"which":[76],"leverages":[77],"frozen":[79],"model":[81],"unlabeled":[83],"parallel":[84],"text-speech":[85],"data":[86,125],"recover":[88],"missing":[89],"inputs.":[92],"Our":[93],"approach":[94],"achieves":[95],"binary":[97],"F-score":[98],"up":[100],"0.71":[102],"for":[103],"annotation":[106],"recovery,":[107],"utilizing":[108],"only":[109],"5-10":[110],"%":[111],"training":[114,122],"data.":[115],"Furthermore,":[116],"subjective":[117],"listening":[118],"tests":[119],"show":[120],"that":[121],"additional":[124],"labeled":[126],"via":[127],"enhances":[129],"overall":[130],"synthesis":[131],"quality,":[132],"as":[133,135],"well":[134],"providing":[136],"good":[137],"control":[138],"plausible-sounding":[140],"focus.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}