{"id":"https://openalex.org/W1961629950","doi":"https://doi.org/10.21437/interspeech.2010-187","title":"The role of higher-level linguistic features in HMM-based speech synthesis","display_name":"The role of higher-level linguistic features in HMM-based speech synthesis","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W1961629950","doi":"https://doi.org/10.21437/interspeech.2010-187","mag":"1961629950"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-187","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/4567","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","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":true,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["School of Philosophy Psychology and Language Sciences"],"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110238677"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.787,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90644084,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"841","last_page":"844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9995999932289124,"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":0.9990000128746033,"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/naturalness","display_name":"Naturalness","score":0.9245908856391907},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7293006181716919},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6661653518676758},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6573975086212158},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6141304969787598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5903186798095703},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5875176787376404},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5607984066009521},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.51609867811203},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.502704381942749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49513188004493713},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48341190814971924},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44555002450942993},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4367651343345642},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.41958779096603394},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.41860824823379517},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3412085473537445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14852380752563477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07265156507492065}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9245908856391907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293006181716919},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6661653518676758},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6573975086212158},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6141304969787598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5903186798095703},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5875176787376404},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5607984066009521},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.51609867811203},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.502704381942749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49513188004493713},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48341190814971924},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44555002450942993},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4367651343345642},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.41958779096603394},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.41860824823379517},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3412085473537445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14852380752563477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07265156507492065},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2010-187","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","pdf_url":"http://hdl.handle.net/1842/4567","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:era.ed.ac.uk:1842/4567","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/4567","pdf_url":null,"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:openaire/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","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":"Watts, O, Yamagishi, J & King, S 2010, The role of higher-level linguistic features in HMM-based speech synthesis. in Proc. Interspeech. pp. 841-844. < http://hdl.handle.net/1842/4567 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/cf2a7a1d-c24c-4b31-8b37-14bdba8581f7","pdf_url":"http://hdl.handle.net/1842/4567","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":""},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1961629950.pdf","grobid_xml":"https://content.openalex.org/works/W1961629950.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W1580849279","https://openalex.org/W1773803948","https://openalex.org/W2042691334","https://openalex.org/W2081687495","https://openalex.org/W2135843243","https://openalex.org/W2158666451","https://openalex.org/W2170980774","https://openalex.org/W2406017614","https://openalex.org/W2950121111","https://openalex.org/W4250788613"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W2507083698","https://openalex.org/W2465473908","https://openalex.org/W4391272374","https://openalex.org/W49590631","https://openalex.org/W1984347656","https://openalex.org/W2474947928","https://openalex.org/W1489682032"],"abstract_inverted_index":{"We":[0],"analyse":[1],"the":[2,8,17,20,34,58,62,111],"contribution":[3],"of":[4,7,11,19,33,61,71,84,107,113,117],"higher-level":[5],"elements":[6],"linguistic":[9,118],"specification":[10],"a":[12,68,105,114],"data-driven":[13],"speech":[14,22],"synthesiser":[15],"to":[16,41],"naturalness":[18],"synthetic":[21],"which":[23,38],"it":[24],"generates.":[25],"The":[26,74],"system":[27,63],"is":[28],"trained":[29],"using":[30],"various":[31],"subsets":[32],"full":[35],"feature-set,":[36],"in":[37,67,86],"features":[39,95],"relating":[40],"syntactic":[42],"category,":[43],"intonational":[44],"phrase":[45],"boundary,":[46],"pitch":[47],"accent":[48],"and":[49],"boundary":[50],"tones":[51],"are":[52,64],"selectively":[53],"removed.":[54],"Utterances":[55],"synthesised":[56],"by":[57],"different":[59,115],"configurations":[60],"then":[65],"compared":[66],"subjective":[69],"evaluation":[70],"their":[72],"naturalness.":[73],"work":[75],"presented":[76],"forms":[77],"background":[78],"analysis":[79],"for":[80,123],"an":[81],"ongoing":[82],"set":[83],"experiments":[85],"performing":[87],"text-to-speech":[88],"(TTS)":[89],"conversion":[90],"based":[91],"on":[92],"shallow":[93],"features:":[94],"that":[96],"can":[97],"be":[98],"trivially":[99],"extracted":[100],"from":[101],"text.":[102],"By":[103],"building":[104],"range":[106],"systems,":[108],"each":[109],"assuming":[110],"availability":[112],"level":[116],"annotation,":[119],"we":[120],"obtain":[121],"benchmarks":[122],"our":[124],"on-going":[125],"work.":[126]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}