{"id":"https://openalex.org/W2154237089","doi":"https://doi.org/10.21437/interspeech.2008-549","title":"Including pitch accent optionality in unit selection text-to-speech synthesis","display_name":"Including pitch accent optionality in unit selection text-to-speech synthesis","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W2154237089","doi":"https://doi.org/10.21437/interspeech.2008-549","mag":"2154237089"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/3901","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063165262","display_name":"Leonardo Badino","orcid":"https://orcid.org/0000-0001-7037-5914"},"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":true,"raw_author_name":"Leonardo Badino","raw_affiliation_strings":["Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084488961","display_name":"Robert A. Clark","orcid":"https://orcid.org/0000-0002-4892-3619"},"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":"Robert A. J. Clark","raw_affiliation_strings":["Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028468680","display_name":"Volker Strom","orcid":null},"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":"Volker Strom","raw_affiliation_strings":["Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063165262"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.5854,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.80087505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2118","last_page":"2121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9988999962806702,"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":0.9984999895095825,"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/speech-synthesis","display_name":"Speech synthesis","score":0.7449965476989746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7058562636375427},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6897363662719727},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6717326045036316},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6465687155723572},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.6246037483215332},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43201589584350586},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4261445701122284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33285340666770935},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.12199443578720093},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10558551549911499}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7449965476989746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058562636375427},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6897363662719727},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6717326045036316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6465687155723572},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.6246037483215332},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43201589584350586},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4261445701122284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33285340666770935},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.12199443578720093},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10558551549911499},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2008-549","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3901","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3901","pdf_url":"http://hdl.handle.net/1842/3901","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ce619941-124d-4171-a315-a29c707769a4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/including-pitch-accent-optionality-in-unit-selection-texttospeech-synthesis(ce619941-124d-4171-a315-a29c707769a4).html","pdf_url":"http://hdl.handle.net/20.500.11820/ce619941-124d-4171-a315-a29c707769a4","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:CiteSeerX.psu:10.1.1.217.3955","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.3955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2008/IS080159.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/ce619941-124d-4171-a315-a29c707769a4","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ce619941-124d-4171-a315-a29c707769a4","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":"Badino, L, Clark, R A J & Strom, V 2008, Including Pitch Accent Optionality in Unit Selection Text-to-Speech Synthesis. in Proc. Interspeech. pp. 2118-2121.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3901","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3901","pdf_url":"http://hdl.handle.net/1842/3901","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2154237089.pdf","grobid_xml":"https://content.openalex.org/works/W2154237089.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1539337024","https://openalex.org/W1548765444","https://openalex.org/W1927421023","https://openalex.org/W1963846260","https://openalex.org/W2004687614","https://openalex.org/W2088965663","https://openalex.org/W2118021002","https://openalex.org/W2285230686","https://openalex.org/W2396901317"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317","https://openalex.org/W2350046259"],"abstract_inverted_index":{"A":[0],"significant":[1],"variability":[2,36,59],"in":[3,41,85],"pitch":[4,117],"accent":[5,61],"placement":[6],"is":[7,52],"found":[8],"when":[9],"comparing":[10],"the":[11,22,58,65,74,98],"patterns":[12],"of":[13,49,60,67,76,82,100],"prosodic":[14,39,86,115],"prominence":[15,40],"realized":[16],"by":[17,54],"different":[18],"English":[19],"speakers":[20],"reading":[21],"same":[23],"sentences.":[24],"In":[25],"this":[26,35],"paper":[27],"we":[28,63],"describe":[29],"a":[30,78,92],"simple":[31],"approach":[32,51,102],"to":[33,37],"incorporate":[34],"synthesize":[38],"unit":[42,113],"selection":[43],"text-to-speech":[44],"synthesis.":[45],"The":[46],"main":[47],"motivation":[48],"our":[50,101],"that":[53],"taking":[55],"into":[56],"account":[57],"placements":[62],"enlarge":[64],"set":[66],"prosodically":[68],"acceptable":[69],"speech":[70,111],"units,":[71,83],"thus":[72],"increasing":[73],"chances":[75],"selecting":[77],"good":[79],"quality":[80],"sequence":[81],"both":[84],"and":[87,103],"segmental":[88],"terms.":[89],"Results":[90],"on":[91],"large":[93],"scale":[94],"perceptual":[95],"test":[96],"show":[97],"benefits":[99],"indicate":[104],"directions":[105],"for":[106],"further":[107],"improvements.":[108],"Index":[109],"Terms:":[110],"synthesis,":[112],"selection,":[114],"prominence,":[116],"accents":[118]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
