{"id":"https://openalex.org/W2160084280","doi":"https://doi.org/10.1109/icassp.2004.1325908","title":"Speaking style adaptation using context clustering decision tree for HMM-based speech synthesis","display_name":"Speaking style adaptation using context clustering decision tree for HMM-based speech synthesis","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2160084280","doi":"https://doi.org/10.1109/icassp.2004.1325908","mag":"2160084280"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","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/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"J. Yamagishi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029705460","display_name":"Makoto Tachibana","orcid":"https://orcid.org/0000-0002-5907-5563"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"M. Tachibana","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064866374","display_name":"Takashi Masuko","orcid":"https://orcid.org/0000-0002-2410-2007"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Masuko","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007639385"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":4.6213,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94856283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"5"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9945999979972839,"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":0.9912999868392944,"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":0.7440017461776733},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7324836254119873},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7199736833572388},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.7007694244384766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6997277140617371},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6386083960533142},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6326988935470581},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6251704096794128},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.5612103343009949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4612857401371002},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4380491077899933},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42513132095336914},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2745363116264343},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21598714590072632}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440017461776733},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7324836254119873},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7199736833572388},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7007694244384766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6997277140617371},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6386083960533142},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6326988935470581},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6251704096794128},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.5612103343009949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4612857401371002},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4380491077899933},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42513132095336914},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2745363116264343},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21598714590072632},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1325908","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107808","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100539609","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W39968598","https://openalex.org/W1861150963","https://openalex.org/W1963627370","https://openalex.org/W2093450784","https://openalex.org/W2097544856","https://openalex.org/W2146871184","https://openalex.org/W2158069733","https://openalex.org/W2166823384","https://openalex.org/W6601608730","https://openalex.org/W6674914289"],"related_works":["https://openalex.org/W2998037107","https://openalex.org/W1569871744","https://openalex.org/W2379437105","https://openalex.org/W2016024526","https://openalex.org/W3139928442","https://openalex.org/W1567336638","https://openalex.org/W3124892642","https://openalex.org/W3125367266","https://openalex.org/W1654902617","https://openalex.org/W3123380490"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,69],"MLLR-based":[4],"speaking":[5,14,38,101],"style":[6,39,72],"adaptation":[7,85],"technique":[8],"for":[9,37,59,109],"HMM-based":[10],"speech":[11,87],"synthesis.":[12],"Since":[13],"styles":[15,102],"and":[16,107,111],"emotional":[17],"expressions":[18],"are":[19,53],"characterized":[20],"by":[21],"many":[22],"suprasegmental":[23,35,43],"features":[24,36],"as":[25,27],"well":[26],"segmental":[28],"features,":[29],"it":[30],"is":[31],"necessary":[32],"to":[33,74,95,98],"adapt":[34,68],"adaptation.":[40],"To":[41],"achieve":[42],"feature":[44],"adaptation,":[45],"we":[46,67],"utilize":[47],"context":[48],"clustering":[49],"decision":[50],"trees,":[51],"which":[52],"constructed":[54],"in":[55],"the":[56,99],"training":[57],"stage,":[58],"tying":[60],"of":[61,105],"regression":[62],"matrices.":[63],"Using":[64],"this":[65],"technique,":[66],"initial":[70],"\"reading\"":[71],"model":[73],"\"joyful\"":[75],"or":[76],"\"sad\"":[77],"styles.":[78],"Experimental":[79],"results":[80],"show":[81],"that,":[82],"using":[83],"50":[84],"sentences,":[86],"samples":[88],"generated":[89],"from":[90],"adapted":[91],"models":[92],"were":[93],"judged":[94],"be":[96],"similar":[97],"target":[100],"at":[103],"rates":[104],"92%":[106],"70%":[108],"joyful":[110],"sad":[112],"styles,":[113],"respectively.":[114]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}