{"id":"https://openalex.org/W1973532181","doi":"https://doi.org/10.1109/icassp.2010.5495141","title":"HMM-based sequence-to-frame mapping for voice conversion","display_name":"HMM-based sequence-to-frame mapping for voice conversion","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1973532181","doi":"https://doi.org/10.1109/icassp.2010.5495141","mag":"1973532181"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495141","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/A5100748135","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0002-1889-2567"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["University of Tokyo, Hongo, Tokyo, Japan","The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["University of Tokyo, Hongo, Tokyo, Japan","The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["University of Tokyo, Hongo, Tokyo, Japan","The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Hongo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"The University of Tokyo, Hongo, Bunkyo-ku, 113-0033, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"4830","last_page":"4833"},"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":0.9991000294685364,"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":0.9951000213623047,"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":0.8889787197113037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701655387878418},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6494894027709961},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6220143437385559},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.614287793636322},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.549077033996582},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5022752285003662},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4811438322067261},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.455385684967041},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4229796230792999}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8889787197113037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701655387878418},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6494894027709961},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6220143437385559},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.614287793636322},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.549077033996582},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5022752285003662},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4811438322067261},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.455385684967041},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4229796230792999},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495141","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.639.9428","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.9428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2010/ICASSP_p4830-4833_t2010-3.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1518567289","https://openalex.org/W1592940279","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2123003832","https://openalex.org/W2125838338","https://openalex.org/W2156142001","https://openalex.org/W2161135987","https://openalex.org/W2166090740","https://openalex.org/W6635329185"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2097963413","https://openalex.org/W2294335174","https://openalex.org/W2025614924","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W1974738623","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Voice":[0],"conversion":[1,110],"can":[2],"be":[3],"reduced":[4],"to":[5,8,62,89,122,162,183],"a":[6,10,49,67,123,133,138],"problem":[7],"find":[9],"transformation":[11],"function":[12,101,136],"between":[13],"the":[14,22,33,44,64,149,164,185],"corresponding":[15],"speech":[16,50,69,77],"sequences":[17],"of":[18,43,66,141,153,166],"two":[19,160],"speakers.":[20],"Perhaps":[21],"most":[23],"voice":[24,93,109,190],"conversions":[25],"methods":[26,111,161],"are":[27,146],"GMM-based":[28,35],"statistical":[29,103],"mapping":[30,36,100,135,168],"methods.":[31],"However,":[32],"classical":[34],"is":[37,53],"frame-to-frame,":[38],"and":[39,71,79,118,158,175],"cannot":[40],"take":[41],"account":[42],"contextual":[45],"information":[46],"existing":[47],"over":[48],"sequence.":[51],"It":[52],"well":[54],"known":[55],"that":[56,112],"HMM":[57,91,150],"yields":[58],"an":[59,97],"efficient":[60],"method":[61,131,188],"model":[63],"density":[65],"whole":[68],"sequence":[70],"has":[72,132],"found":[73],"great":[74],"successes":[75],"in":[76],"recognition":[78],"synthesis.":[80],"Inspired":[81],"by":[82],"this":[83,85],"fact,":[84],"paper":[86],"studies":[87],"how":[88],"use":[90],"for":[92,116,189],"conversion.":[94,191],"We":[95,155,179],"derive":[96],"HMM-based":[98,108,187],"sequence-to-frame":[99],"with":[102,125],"analysis.":[104],"Different":[105],"from":[106],"previous":[107],"used":[113],"forced":[114],"alignment":[115],"segmentation":[117],"transform":[119],"frames":[120],"aligned":[121],"state":[124],"its":[126],"associated":[127],"linear":[128,142],"transformation,":[129],"our":[130,167],"soft":[134],"as":[137,148],"weighted":[139],"summation":[140],"transformations.":[143],"The":[144],"weights":[145],"calculated":[147],"posterior":[151],"probabilities":[152],"frames.":[154],"also":[156],"propose":[157],"compare":[159],"learn":[163],"parameters":[165],"functions,":[169],"namely":[170],"least":[171],"square":[172],"error":[173],"estimation":[174],"maximum":[176],"likelihood":[177],"estimation.":[178],"carried":[180],"out":[181],"experiments":[182],"examine":[184],"proposed":[186]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}