{"id":"https://openalex.org/W2401700297","doi":"https://doi.org/10.21437/interspeech.2011-45","title":"HMM-based emphatic speech synthesis using unsupervised context labeling","display_name":"HMM-based emphatic speech synthesis using unsupervised context labeling","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2401700297","doi":"https://doi.org/10.21437/interspeech.2011-45","mag":"2401700297"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5042527524","display_name":"Yu Maeno","orcid":"https://orcid.org/0000-0001-7754-0054"},"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":"Yu Maeno","raw_affiliation_strings":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","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":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035788151","display_name":"Hideharu Nakajima","orcid":"https://orcid.org/0000-0001-8320-7442"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hideharu Nakajima","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102842694","display_name":"Hideyuki Mizuno","orcid":"https://orcid.org/0000-0002-2591-7152"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hideyuki Mizuno","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082610849","display_name":"Osamu Yoshioka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osamu Yoshioka","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.8361,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.95252395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1849","last_page":"1852"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9979000091552734,"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":0.9977999925613403,"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":0.8108325600624084},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.8046261072158813},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7915928363800049},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7210133075714111},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6300222873687744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914338231086731},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5555835962295532},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48877665400505066},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4886758625507355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108325600624084},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.8046261072158813},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7915928363800049},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7210133075714111},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6300222873687744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914338231086731},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5555835962295532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48877665400505066},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4886758625507355},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.21437/interspeech.2011-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W45989781","https://openalex.org/W1492653331","https://openalex.org/W1494687963","https://openalex.org/W1525502786","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2048389584","https://openalex.org/W2049686551","https://openalex.org/W2061760940","https://openalex.org/W2085013480","https://openalex.org/W2093265061","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,41,50],"approach":[4],"to":[5,91],"HMM-based":[6,109],"expressive":[7,112],"speech":[8,24,38,102,110],"synthesis":[9],"which":[10],"does":[11],"not":[12],"require":[13],"any":[14],"supervised":[15],"labeling":[16,37,52,77,88,93],"process":[17],"for":[18,36,44,74],"emphasis":[19,42,56,76,105,114],"context.":[20],"We":[21],"use":[22],"appealing-style":[23],"whose":[25],"sentences":[26],"were":[27],"taken":[28],"from":[29],"real":[30],"domains.":[31],"To":[32],"reduce":[33],"the":[34,45,55,60,72,75,86,92],"cost":[35],"data":[39],"with":[40],"context":[43,57],"model":[46],"training,":[47],"we":[48],"propose":[49],"unsupervised":[51,87,116],"technique":[53],"of":[54,68,101],"based":[58],"on":[59],"difference":[61],"between":[62],"original":[63],"and":[64,104],"generated":[65],"F0":[66,118],"patterns":[67],"training":[69],"sentences.":[70],"Although":[71],"criterion":[73],"is":[78,89],"quite":[79],"simple,":[80],"subjective":[81],"evaluation":[82],"results":[83],"reveal":[84],"that":[85],"comparable":[90],"conducted":[94],"carefully":[95],"by":[96],"a":[97],"human":[98],"in":[99],"terms":[100],"naturalness":[103],"reproducibility.":[106],"Index":[107],"Terms:":[108],"synthesis,":[111],"speech,":[113],"expression,":[115],"labeling,":[117],"generation":[119]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
