{"id":"https://openalex.org/W2401293599","doi":"https://doi.org/10.1109/icassp.2016.7472735","title":"Speaker adaptive model based on Boltzmann machine for non-parallel training in voice conversion","display_name":"Speaker adaptive model based on Boltzmann machine for non-parallel training in voice conversion","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2401293599","doi":"https://doi.org/10.1109/icassp.2016.7472735","mag":"2401293599"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications, Graduate School of Information Systems"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Graduate School of Information Systems","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008413640","display_name":"Yasuhiro Minami","orcid":"https://orcid.org/0000-0003-3514-4285"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Minami","raw_affiliation_strings":["The University of Electro-Communications, Graduate School of Information Systems"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications, Graduate School of Information Systems","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041887072"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":1.2854,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86502197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"5530","last_page":"5534"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8134157657623291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7036147117614746},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.48886555433273315},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45917749404907227},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4371161460876465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.361266165971756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3236737847328186},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1499568223953247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134157657623291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7036147117614746},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.48886555433273315},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45917749404907227},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4371161460876465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.361266165971756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3236737847328186},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1499568223953247},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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.2016.7472735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W10800834","https://openalex.org/W17772838","https://openalex.org/W49412823","https://openalex.org/W1517766716","https://openalex.org/W1588266896","https://openalex.org/W1599512239","https://openalex.org/W1950777589","https://openalex.org/W1963778986","https://openalex.org/W1972420736","https://openalex.org/W2009272428","https://openalex.org/W2017425464","https://openalex.org/W2022125261","https://openalex.org/W2105160541","https://openalex.org/W2120605154","https://openalex.org/W2122565151","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2129863563","https://openalex.org/W2131062138","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2153057929","https://openalex.org/W2156142001","https://openalex.org/W2294351487","https://openalex.org/W2401544731","https://openalex.org/W2404719220","https://openalex.org/W2407110532","https://openalex.org/W2577350056","https://openalex.org/W2913399920","https://openalex.org/W4244017338","https://openalex.org/W6631184128","https://openalex.org/W6635216677","https://openalex.org/W6678281641","https://openalex.org/W6679486525","https://openalex.org/W6680066585","https://openalex.org/W6696767757","https://openalex.org/W6713064456","https://openalex.org/W6732045268"],"related_works":["https://openalex.org/W2916681395","https://openalex.org/W2529583158","https://openalex.org/W2963348254","https://openalex.org/W1641020902","https://openalex.org/W2133316674","https://openalex.org/W230091440","https://openalex.org/W1575733688","https://openalex.org/W3121130100","https://openalex.org/W4394050964","https://openalex.org/W2551249631"],"abstract_inverted_index":{"In":[0,131,176],"this":[1],"paper,":[2],"we":[3,134],"present":[4],"a":[5,23,123,149,179,203],"voice":[6],"conversion":[7,177],"(VC)":[8],"method":[9,227],"that":[10,157,196,216,228],"does":[11],"not":[12,118],"use":[13,66,120],"any":[14],"parallel":[15,49,68,121,230],"data":[16,53,69,77],"while":[17,35],"training":[18,71,81,138,142],"the":[19,37,43,55,61,65,76,80,85,89,96,101,136,154,190,198,210,223,234],"model.":[20],"VC":[21,45,117],"is":[22,33,82,92,126,183,193,206],"technique":[24],"where":[25],"only":[26,93],"speaker":[27,97],"specific":[28],"information":[29,39,160,163,192],"in":[30,70,100,106,116],"source":[31,56],"speech":[32,52,181,205],"converted":[34],"keeping":[36],"phonological":[38,159,186],"unchanged.":[40],"Most":[41],"of":[42,51,67,197,222],"existing":[44],"methods":[46],"rely":[47],"on":[48,140,153],"data-pairs":[50],"from":[54],"and":[57,103,161,167,187,201],"target":[58],"speakers":[59],"uttering":[60],"same":[62],"sentences.":[63],"However,":[64],"causes":[72],"several":[73],"problems;":[74],"1)":[75],"used":[78,99,229],"for":[79],"limited":[83],"to":[84,95,119,129],"pre-defined":[86],"sentences,":[87],"2)":[88],"trained":[90,173],"model":[91,151],"applied":[94],"pair":[98],"training,":[102],"3)":[104],"mismatch":[105],"alignment":[107],"may":[108],"happen.":[109],"Although":[110],"it":[111],"is,":[112],"thus,":[113],"fairy":[114],"preferable":[115],"data,":[122,231],"non-parallel":[124,137,236],"approach":[125,218],"considered":[127],"difficult":[128],"learn.":[130],"our":[132,217],"approach,":[133],"realize":[135],"based":[139,152],"speaker-adaptive":[141],"(SAT).":[143],"Speech":[144],"signals":[145],"are":[146,171],"represented":[147],"using":[148,174],"probabilistic":[150],"Boltzmann":[155],"machine":[156],"defines":[158],"speaker-related":[162,188,191],"explicitly.":[164],"Speaker-independent":[165],"(SI)":[166],"speaker-dependent":[168],"(SD)":[169],"parameters":[170],"simultaneously":[172],"SAT.":[175],"stage,":[178],"given":[180],"signal":[182],"decomposed":[184],"into":[185],"information,":[189],"replaced":[194],"with":[195],"desired":[199],"speaker,":[200],"then":[202],"voice-converted":[204],"obtained":[207],"by":[208],"mixing":[209],"two.":[211],"Our":[212],"experimental":[213],"results":[214],"showed":[215],"unfortunately":[219],"fell":[220],"short":[221],"popular":[224],"conventional":[225,235],"GMM-based":[226],"but":[232],"outperformed":[233],"approach.":[237]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}