{"id":"https://openalex.org/W2158942523","doi":"https://doi.org/10.1109/icassp.2006.1659961","title":"HSMM-Based Model Adaptation Algorithms for Average-Voice-Based Speech Synthesis","display_name":"HSMM-Based Model Adaptation Algorithms for Average-Voice-Based Speech Synthesis","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2158942523","doi":"https://doi.org/10.1109/icassp.2006.1659961","mag":"2158942523"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1659961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5112480247","display_name":"Kei Ogata","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":"K. Ogata","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/A5024469014","display_name":"Yuji Nakano","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":"Y. Nakano","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/A5033660872","display_name":"Juri Isogai","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":"J. Isogai","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":5,"corresponding_author_ids":["https://openalex.org/A5007639385"],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":6.7773,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96714332,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9936000108718872,"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":0.9927999973297119,"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":0.825941801071167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7814021110534668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7794946432113647},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6395325064659119},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.569010853767395},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4725363552570343},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4279102683067322},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4203609526157379}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.825941801071167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7814021110534668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7794946432113647},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6395325064659119},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.569010853767395},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4725363552570343},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4279102683067322},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4203609526157379},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1659961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1659961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W108537639","https://openalex.org/W175280642","https://openalex.org/W1500184319","https://openalex.org/W1600722501","https://openalex.org/W1602430027","https://openalex.org/W1605997703","https://openalex.org/W2002342963","https://openalex.org/W2064218608","https://openalex.org/W2081976287","https://openalex.org/W2146871184","https://openalex.org/W2149175990","https://openalex.org/W2167152389","https://openalex.org/W2484208911","https://openalex.org/W6604406228","https://openalex.org/W6607096815","https://openalex.org/W6636404455","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W1992908141","https://openalex.org/W2380970022","https://openalex.org/W642007152","https://openalex.org/W4253660971","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619"],"abstract_inverted_index":{"In":[0,30],"HMM-based":[1],"speech":[2,12,21,26,41,54,78,88,98],"synthesis,":[3],"we":[4],"have":[5],"to":[6,23,72],"choose":[7],"the":[8,17,87],"modeling":[9,33],"strategy":[10],"for":[11,38,76,83],"synthesis":[13,99],"units":[14],"depending":[15],"on":[16],"amount":[18,85],"of":[19,27,56,86,107],"available":[20,53],"data":[22,55],"generate":[24],"synthetic":[25],"better":[28],"quality.":[29],"general,":[31],"speaker-dependent":[32],"is":[34,60],"an":[35],"ideal":[36],"choice":[37],"a":[39,57,80],"large":[40],"data,":[42],"whereas":[43],"speaker":[44,59,66],"adaptation":[45,67,93],"with":[46],"average":[47],"voice":[48],"model":[49],"becomes":[50],"promising":[51],"when":[52],"target":[58],"limited.":[61],"This":[62],"paper":[63],"describes":[64],"several":[65,108],"algorithms":[68,94],"and":[69,101],"MAP":[70],"modification":[71],"develop":[73],"consistent":[74],"method":[75],"synthesizing":[77],"in":[79],"unified":[81],"way":[82],"arbitrary":[84],"data.":[89],"We":[90],"incorporate":[91],"these":[92],"into":[95],"our":[96],"HSMM-based":[97],"system":[100],"show":[102],"its":[103],"effectiveness":[104],"from":[105],"results":[106],"evaluation":[109],"tests":[110]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}