{"id":"https://openalex.org/W4385993782","doi":"https://doi.org/10.21437/ssw.2023-12","title":"Synthesising turn-taking cues using natural conversational data","display_name":"Synthesising turn-taking cues using natural conversational data","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385993782","doi":"https://doi.org/10.21437/ssw.2023-12"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2023-12","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-12","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","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/files/378478105/O_MahonyEtal2023SynthesisingTurn_Taking.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072423792","display_name":"Johannah O\u2019Mahony","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Johannah O'Mahony","raw_affiliation_strings":["Centre for Speech Technology Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011726172","display_name":"Catherine Lai","orcid":"https://orcid.org/0000-0001-8861-0281"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catherine Lai","raw_affiliation_strings":["Centre for Speech Technology Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, United Kingdom","institution_ids":[]}]},{"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":["Centre for Speech Technology Research, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, United Kingdom","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5072423792"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9108798503875732},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8276796936988831},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7828758955001831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023007869720459},{"id":"https://openalex.org/keywords/realisation","display_name":"Realisation","score":0.6956912279129028},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6835544109344482},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5501691102981567},{"id":"https://openalex.org/keywords/turn-taking","display_name":"Turn-taking","score":0.5470104217529297},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.5340280532836914},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.5291830897331238},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36594071984291077},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3475736975669861},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3194810152053833},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.22831609845161438}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9108798503875732},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8276796936988831},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7828758955001831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023007869720459},{"id":"https://openalex.org/C2779462738","wikidata":"https://www.wikidata.org/wiki/Q17146409","display_name":"Realisation","level":2,"score":0.6956912279129028},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6835544109344482},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5501691102981567},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.5470104217529297},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.5340280532836914},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.5291830897331238},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36594071984291077},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3475736975669861},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3194810152053833},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.22831609845161438},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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:10.21437/ssw.2023-12","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-12","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/eb6f5873-0dc4-4635-b056-30cf739da54f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/378478105/O_MahonyEtal2023SynthesisingTurn_Taking.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"O'Mahony, J, Lai, C & King, S 2023, Synthesising turn-taking cues using natural conversational data. in G Bailly, T Hueber, D Lolive, N Obin & O Perrotin (eds), Proceedings of the 12th ISCA Speech Synthesis Workshop : (SSW2023). Proceedings of the ISCA Workshop, Grenoble, pp. 75-80, 12th ISCA Speech Synthesis Workshop , Grenoble, France, 26/08/23. https://doi.org/10.21437/SSW.2023-12","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/eb6f5873-0dc4-4635-b056-30cf739da54f","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/eb6f5873-0dc4-4635-b056-30cf739da54f","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/eb6f5873-0dc4-4635-b056-30cf739da54f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/eb6f5873-0dc4-4635-b056-30cf739da54f","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"O'Mahony, J, Lai, C & King, S 2023, Synthesising turn-taking cues using natural conversational data. in G Bailly, T Hueber, D Lolive, N Obin & O Perrotin (eds), Proceedings of the 12th ISCA Speech Synthesis Workshop : (SSW2023). Proceedings of the ISCA Workshop, Grenoble, pp. 75-80, 12th ISCA Speech Synthesis Workshop , Grenoble, France, 26/08/23. https://doi.org/10.21437/SSW.2023-12","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/eb6f5873-0dc4-4635-b056-30cf739da54f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/files/378478105/O_MahonyEtal2023SynthesisingTurn_Taking.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"O'Mahony, J, Lai, C & King, S 2023, Synthesising turn-taking cues using natural conversational data. in G Bailly, T Hueber, D Lolive, N Obin & O Perrotin (eds), Proceedings of the 12th ISCA Speech Synthesis Workshop : (SSW2023). Proceedings of the ISCA Workshop, Grenoble, pp. 75-80, 12th ISCA Speech Synthesis Workshop , Grenoble, France, 26/08/23. https://doi.org/10.21437/SSW.2023-12","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1590744681","https://openalex.org/W1974537583","https://openalex.org/W2001292406","https://openalex.org/W2019528670","https://openalex.org/W2044196055","https://openalex.org/W2467926808","https://openalex.org/W2526351692","https://openalex.org/W2745531599","https://openalex.org/W2747874407","https://openalex.org/W2972355799","https://openalex.org/W2973177710","https://openalex.org/W3089817844","https://openalex.org/W3092028330","https://openalex.org/W3112188842","https://openalex.org/W3150572638","https://openalex.org/W3151309757","https://openalex.org/W3193700177","https://openalex.org/W3197861989","https://openalex.org/W3198152857","https://openalex.org/W3208708812","https://openalex.org/W4225300652","https://openalex.org/W4283662594","https://openalex.org/W4296068977","https://openalex.org/W4299687266","https://openalex.org/W4362465934","https://openalex.org/W4389009518","https://openalex.org/W4390926723"],"related_works":["https://openalex.org/W1984347656","https://openalex.org/W169399214","https://openalex.org/W258725851","https://openalex.org/W2903456225","https://openalex.org/W4389009518","https://openalex.org/W1978877097","https://openalex.org/W3208962307","https://openalex.org/W4295682112","https://openalex.org/W2595453317","https://openalex.org/W3182597358"],"abstract_inverted_index":{"As":[0],"speech":[1,103],"synthesis":[2,18,104],"quality":[3],"reaches":[4],"high":[5],"levels":[6],"of":[7,19,25,53],"naturalness":[8],"for":[9],"isolated":[10],"utterances,":[11],"more":[12],"work":[13],"is":[14,29,98,110],"focusing":[15],"on":[16,106],"the":[17,54,70,85,94,123],"context-dependent":[20],"conversational":[21],"speech.":[22],"The":[23],"role":[24],"context":[26,46,71],"in":[27,60],"conversation":[28],"still":[30],"poorly":[31],"understood":[32],"and":[33,114],"many":[34],"contextual":[35,91],"factors":[36],"can":[37,125],"affect":[38],"an":[39,78,108],"utterances\u2019s":[40],"prosodic":[41],"realisation.":[42,80],"Most":[43],"studies":[44,64],"incorporating":[45],"use":[47],"rich":[48],"acoustic":[49],"or":[50,74],"textual":[51],"embeddings":[52],"previous":[55],"context,":[56],"then":[57],"demonstrate":[58,121],"improvements":[59],"overall":[61],"naturalness.":[62],"Such":[63],"are":[65,118,130],"not":[66],"informative":[67],"about":[68],"what":[69],"embedding":[72],"represents,":[73],"how":[75],"it":[76],"affects":[77],"utterance\u2019s":[79],"So":[81],"instead,":[82],"we":[83],"narrow":[84],"focus":[86],"to":[87,120],"a":[88,102],"single,":[89],"explicit":[90],"factor.":[92],"In":[93],"current":[95],"work,":[96],"this":[97],"turn-taking.":[99],"We":[100],"condition":[101],"model":[105,124],"whether":[107],"utterance":[109],"turn-final.":[111],"Objective":[112],"measures":[113],"targeted":[115],"subjective":[116],"evaluation":[117],"used":[119],"that":[122],"synthesise":[126],"turn-taking":[127],"cues":[128],"which":[129],"perceived":[131],"by":[132],"listeners,":[133],"with":[134],"results":[135],"being":[136],"speaker-dependent.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}