{"id":"https://openalex.org/W283597454","doi":"https://doi.org/10.21437/interspeech.2014-200","title":"Dialogue context sensitive speech synthesis using factorized decision trees","display_name":"Dialogue context sensitive speech synthesis using factorized decision trees","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W283597454","doi":"https://doi.org/10.21437/interspeech.2014-200","mag":"283597454"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027494724","display_name":"Pirros Tsiakoulis","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pirros Tsiakoulis","raw_affiliation_strings":["University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109274487","display_name":"Catherine Breslin","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Catherine Breslin","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008275428","display_name":"Milomir Ga\u0161i\u0107","orcid":"https://orcid.org/0000-0001-6136-4172"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Ga\u0161i\u0107","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045402928","display_name":"Matthew Henderson","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Henderson","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114246723","display_name":"Dongho Kim","orcid":"https://orcid.org/0000-0003-3911-8746"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongho Kim","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112097289","display_name":"Steve Young","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Young","raw_affiliation_strings":["University of Cambridge, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2937","last_page":"2941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9997000098228455,"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":0.9980000257492065,"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":0.7610710859298706},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.7532740235328674},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.7317712306976318},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7201324701309204},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6920545101165771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5568990111351013},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5233237743377686},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4541548788547516},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4540943503379822},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4509741961956024},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42863136529922485},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41640448570251465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40737485885620117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38654500246047974},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12679284811019897},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12151005864143372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11020302772521973},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.06457796692848206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610710859298706},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.7532740235328674},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.7317712306976318},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7201324701309204},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6920545101165771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5568990111351013},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5233237743377686},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4541548788547516},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4540943503379822},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4509741961956024},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42863136529922485},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41640448570251465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40737485885620117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38654500246047974},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12679284811019897},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12151005864143372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11020302772521973},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.06457796692848206},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2014-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.466.7742","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.466.7742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mi.eng.cam.ac.uk/research/dialogue/papers/tgbh14.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:660715","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/660715/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W9230629","https://openalex.org/W16234320","https://openalex.org/W44352932","https://openalex.org/W49393394","https://openalex.org/W102921666","https://openalex.org/W1494687963","https://openalex.org/W1577202350","https://openalex.org/W1973933596","https://openalex.org/W2008406816","https://openalex.org/W2025638820","https://openalex.org/W2029434926","https://openalex.org/W2034202652","https://openalex.org/W2039800941","https://openalex.org/W2048389584","https://openalex.org/W2071660759","https://openalex.org/W2089704690","https://openalex.org/W2093265061","https://openalex.org/W2101762720","https://openalex.org/W2111284386","https://openalex.org/W2127215649","https://openalex.org/W2127530508","https://openalex.org/W2150775217","https://openalex.org/W2158086337","https://openalex.org/W2283817422","https://openalex.org/W2399355197","https://openalex.org/W2467702943","https://openalex.org/W2529813701","https://openalex.org/W2915960560","https://openalex.org/W3089157195"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1,47],"extends":[2],"our":[3],"recent":[4],"work":[5],"on":[6],"rich":[7],"context":[8,34,171],"utilization":[9],"for":[10,96,133,156],"expressive":[11,164],"speech":[12,165,169],"synthesis":[13],"in":[14,18,43,55,110,124,140,145],"spoken":[15],"dialogue":[16,33,52,73],"systems":[17],"which":[19,77],"significant":[20,108,129,154],"improvements":[21],"to":[22,70,81],"the":[23,36,49,86,111,115,125,136,141,146,157],"appropriateness":[24],"of":[25,51,135],"HMM-based":[26,163],"synthetic":[27,75],"voices":[28,54,137],"were":[29,94],"achieved":[30],"by":[31],"introducing":[32],"into":[35],"decision":[37,88],"tree":[38,89],"state":[39],"clustering":[40],"stage.":[41],"Continuing":[42],"this":[44,46],"direction,":[45],"investigates":[48],"performance":[50],"context-sensitive":[53,74,168],"different":[56,98],"domains.":[57,99],"The":[58,100],"Context":[59],"Adaptive":[60],"Training":[61],"with":[62,118],"Factorized":[63],"Decision":[64],"trees":[65,176],"(FD-CAT)":[66],"approach":[67],"was":[68,78,131],"used":[69],"train":[71],"a":[72,82,152],"voice":[76],"then":[79],"compared":[80],"baseline":[83],"system":[84],"using":[85],"standard":[87],"approach.":[90],"Preference-based":[91],"listening":[92],"tests":[93],"conducted":[95],"two":[97],"first":[101],"domain":[102,143],"concerned":[103],"restaurant":[104,142],"information":[105],"and":[106],"had":[107,121],"coverage":[109,123],"training":[112,126],"data,":[113],"while":[114],"second":[116],"dealing":[117],"appointment":[119,147],"bookings":[120],"minimal":[122],"data.":[127],"No":[128],"preference":[130,155],"found":[132],"any":[134],"when":[138],"tested":[139],"whereas":[144],"booking":[148],"domain,":[149],"listeners":[150],"showed":[151],"statistically":[153],"adaptively":[158],"trained":[159],"voice.":[160],"Index":[161],"Terms:":[162],"synthesis,":[166,170],"dia-logue":[167],"adaptive":[172],"train-ing,":[173],"factorized":[174],"fecision":[175],"1.":[177]},"counts_by_year":[{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}