{"id":"https://openalex.org/W1996550570","doi":"https://doi.org/10.1109/icassp.2010.5495548","title":"HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model","display_name":"HMM-based speech synthesis with unsupervised labeling of accentual context based on F0 quantization and average voice model","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1996550570","doi":"https://doi.org/10.1109/icassp.2010.5495548","mag":"1996550570"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/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","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 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"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029573044","display_name":"Koujirou Ooki","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":"Koujirou Ooki","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 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"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 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","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 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"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 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":1.9073,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86786164,"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":"4622","last_page":"4625"},"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":0.992900013923645,"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":0.98580002784729,"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-recognition","display_name":"Speech recognition","score":0.783248782157898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7721723318099976},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7462859749794006},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6730244159698486},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.6370118260383606},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5825722217559814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5602625012397766},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5487105846405029},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5117842555046082},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5098754167556763},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4276338517665863},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3863796889781952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3700026273727417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09489971399307251},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0876503586769104},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06210285425186157}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.783248782157898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721723318099976},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7462859749794006},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6730244159698486},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.6370118260383606},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5825722217559814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5602625012397766},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5487105846405029},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5117842555046082},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5098754167556763},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4276338517665863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3863796889781952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3700026273727417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09489971399307251},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0876503586769104},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06210285425186157},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1573315856","https://openalex.org/W1593598571","https://openalex.org/W1600722501","https://openalex.org/W1602430027","https://openalex.org/W2085013480","https://openalex.org/W2097544856","https://openalex.org/W2106792148","https://openalex.org/W2120605154","https://openalex.org/W2147779839","https://openalex.org/W4301420498","https://openalex.org/W6636404455"],"related_works":["https://openalex.org/W4367680763","https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2535098683","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W2437596814","https://openalex.org/W2085373452","https://openalex.org/W2183954062"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,66,105],"HMM-based":[4],"speech":[5,78],"synthesis":[6],"technique":[7,33],"without":[8],"any":[9],"manual":[10],"labeling":[11,56],"of":[12,29,40,57],"accent":[13,41,81],"information":[14,82],"for":[15,43,60,90],"a":[16,99,120],"target":[17],"speaker's":[18],"training":[19,61],"data.":[20,62],"To":[21],"appropriately":[22],"model":[23,69],"the":[24,31,44,55,87,93,111,115,124,131,144],"fundamental":[25],"frequency":[26],"(F0)":[27],"feature":[28],"speech,":[30,65],"proposed":[32],"uses":[34],"coarsely":[35],"quantized":[36,125],"F0":[37,49,58,106,126,133],"symbols":[38,127],"instead":[39],"types":[42],"context-dependent":[45],"labeling.":[46],"By":[47],"using":[48,73],"quantization,":[50],"we":[51],"can":[52],"automatically":[53],"conduct":[54,136],"contexts":[59],"When":[63],"synthesizing":[64],"average":[67,116],"voice":[68,117],"trained":[70],"in":[71],"advance":[72],"manually":[74],"labeled":[75],"multiple":[76],"speakers'":[77],"data":[79],"including":[80,123],"is":[83,96,108,128],"used":[84],"to":[85,98],"create":[86],"label":[88,102,112,121],"sequence":[89,113,122],"synthesis.":[91],"Specifically,":[92],"input":[94],"text":[95],"converted":[97],"full":[100],"context":[101],"sequence,":[103],"and":[104,114,138,142],"contour":[107],"generated":[109,132],"from":[110,130],"model.":[118],"Then,":[119],"created":[129],"contour.":[134],"We":[135],"objective":[137],"subjective":[139],"evaluation":[140],"tests,":[141],"discuss":[143],"results.":[145]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}