{"id":"https://openalex.org/W107113854","doi":"https://doi.org/10.21437/interspeech.2004-657","title":"A study on automatic detection of Japanese vowel devoicing for speech synthesis","display_name":"A study on automatic detection of Japanese vowel devoicing for speech synthesis","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W107113854","doi":"https://doi.org/10.21437/interspeech.2004-657","mag":"107113854"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-657","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103146649","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0003-3789-4055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100888269","display_name":"Jinfu Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfu Ni","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102734836","display_name":"Ren-Hua Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renhua Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01286698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2721","last_page":"2724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9890999794006348,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9858999848365784,"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/voice","display_name":"Voice","score":0.8461669087409973},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7979225516319275},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7770136594772339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7448118925094604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7154924869537354},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6328291893005371},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45520830154418945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4531328082084656},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.37446919083595276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3399679958820343}],"concepts":[{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.8461669087409973},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7979225516319275},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7770136594772339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7448118925094604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7154924869537354},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6328291893005371},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45520830154418945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4531328082084656},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.37446919083595276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3399679958820343}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-657","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W126835262","https://openalex.org/W1489183891","https://openalex.org/W2115678687","https://openalex.org/W2286957718"],"related_works":["https://openalex.org/W1552486200","https://openalex.org/W4298401218","https://openalex.org/W2035225705","https://openalex.org/W4250084929","https://openalex.org/W2029185908","https://openalex.org/W1966580183","https://openalex.org/W2605651463","https://openalex.org/W4237603214","https://openalex.org/W2990225429","https://openalex.org/W2904846757"],"abstract_inverted_index":{"In":[0,40],"corpus-based":[1],"speech":[2,9,14],"synthesis,":[3],"the":[4,7,13,17,26,37,45,63,66,82,94,110,116,119,124,134,138,144,151,161],"quality":[5],"of":[6,52],"synthetic":[8],"critically":[10],"depends":[11],"on":[12],"corpus.":[15],"Since":[16],"high":[18,107],"vowel":[19,113,117,152],"in":[20,25,36,97],"Japanese":[21],"might":[22],"be":[23],"devoiced":[24,73],"real":[27],"speech,":[28],"we":[29,43],"should":[30],"detect":[31],"and":[32,48,88,137],"transcribe":[33],"them":[34],"automatically":[35],"corpus":[38],"construction.":[39],"this":[41],"paper,":[42],"apply":[44],"HMM-based":[46],"method,":[47],"adopt":[49],"two":[50],"kinds":[51],"likelihood":[53,95,139],"differences":[54,96,140],"as":[55],"voicing":[56,135,162],"measures":[57],"for":[58,105,150],"different":[59,103],"focuses.":[60],"To":[61],"improve":[62,123],"detection":[64,125,145],"performance,":[65],"discriminative":[67,120],"training":[68,121],"is":[69,112,147,155],"applied":[70],"to":[71,127],"voiced/":[72],"HMM":[74],"training.":[75],"Moreover,":[76],"some":[77],"features":[78,136],"that":[79],"can":[80,122],"discriminate":[81],"voiced/devoiced":[83],"units,":[84],"including":[85],"duration,":[86],"energy":[87],"autocorrelation,":[89],"are":[90],"incorporated":[91],"together":[92],"with":[93,141,160],"several":[98],"methods.":[99],"The":[100],"experiments":[101],"show":[102],"results":[104],"each":[106],"vowel,":[108],"i.e.":[109],"devoicing":[111],"dependent.":[114],"For":[115],"/i/,":[118],"performance":[126],"a":[128],"certain":[129],"degree.":[130],"And":[131],"by":[132],"cumulating":[133],"optimized":[142],"weights,":[143],"accuracy":[146],"improved.":[148],"But":[149],"/u/,":[153],"there":[154],"very":[156],"limited":[157],"improvement,":[158],"even":[159],"features.":[163]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}