{"id":"https://openalex.org/W2160379050","doi":"https://doi.org/10.1109/icassp.2008.4518689","title":"Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis","display_name":"Speaker and style adaptation using average voice model for style control in HMM-based speech synthesis","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2160379050","doi":"https://doi.org/10.1109/icassp.2008.4518689","mag":"2160379050"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518689","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/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":"Makoto Tachibana","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"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/A5111978488","display_name":"S. Izawa","orcid":null},"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":"Shinsuke Izawa","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"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/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"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":"Takashi Nose","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"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":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":1.7626,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85953782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4633","last_page":"4636"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8513365983963013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8162990212440491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7922662496566772},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6499625444412231},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.605504035949707},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5734397768974304},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5522605180740356},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.5085691213607788},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.41523829102516174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3563537001609802}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8513365983963013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8162990212440491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922662496566772},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6499625444412231},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.605504035949707},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5734397768974304},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5522605180740356},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.5085691213607788},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.41523829102516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3563537001609802},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518689","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"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":14,"referenced_works":["https://openalex.org/W284180566","https://openalex.org/W300119222","https://openalex.org/W1602430027","https://openalex.org/W1978136968","https://openalex.org/W1984905644","https://openalex.org/W2039800941","https://openalex.org/W2048973497","https://openalex.org/W2102146461","https://openalex.org/W2147779839","https://openalex.org/W2150791533","https://openalex.org/W2484208911","https://openalex.org/W6610316872","https://openalex.org/W6610697106","https://openalex.org/W6636404455"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,43,60],"technique":[3,22,88],"for":[4,23],"synthesizing":[5],"speech":[6,34,58,93],"with":[7,59,98],"desired":[8],"style":[9,76],"expressivity":[10],"of":[11,32,73],"an":[12,18,78],"arbitrary":[13],"target":[14,62],"speaker's":[15,46,63],"voice.":[16,64],"In":[17],"MLLR-based":[19],"speaker":[20,74,99],"adaptation":[21,72,100],"multiple":[24],"regression":[25],"hidden":[26],"semi-Markov":[27],"model":[28],"(MRHSMM),":[29],"the":[30,38,86,95],"quality":[31],"synthesized":[33],"crucially":[35],"depends":[36],"on":[37],"initial":[39],"MRHSMM":[40],"trained":[41],"from":[42,77],"certain":[44],"source":[45],"data":[47],"and":[48,75],"it":[49],"is":[50],"not":[51],"always":[52],"possible":[53],"to":[54],"synthesize":[55],"natural":[56,91],"sounding":[57,92],"given":[61],"To":[65],"overcome":[66],"this":[67],"problem,":[68],"we":[69],"perform":[70],"simultaneous":[71],"average":[79],"voice":[80],"model.":[81],"Experimental":[82],"results":[83],"show":[84],"that":[85],"proposed":[87],"provides":[89],"more":[90],"than":[94],"conventional":[96],"one":[97],"only.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}