{"id":"https://openalex.org/W2897614477","doi":"https://doi.org/10.1109/taslp.2018.2877465","title":"Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra","display_name":"Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra","publication_year":2018,"publication_date":"2018-10-22","ids":{"openalex":"https://openalex.org/W2897614477","doi":"https://doi.org/10.1109/taslp.2018.2877465","mag":"2897614477"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2877465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877465","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/7e177912-d04d-4d77-af2d-9592495f676c","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1863-6771","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics and Engineering, The University of Electro-Communications, Tokyo, Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2752-3955","affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6561,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.6966443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"27","issue":"2","first_page":"244","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9980999827384949,"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/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.7480393052101135},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5736231207847595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5630640387535095},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.5264407396316528},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5253462195396423},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4964035153388977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4875604510307312},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4816373884677887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46515995264053345},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4128142297267914},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.40120911598205566},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3325366675853729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20956552028656006}],"concepts":[{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.7480393052101135},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5736231207847595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5630640387535095},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.5264407396316528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5253462195396423},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4964035153388977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4875604510307312},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4816373884677887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46515995264053345},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4128142297267914},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40120911598205566},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3325366675853729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20956552028656006},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2018.2877465","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2877465","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/7e177912-d04d-4d77-af2d-9592495f676c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7e177912-d04d-4d77-af2d-9592495f676c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nakashika, T, Takaki, S & Yamagishi, J 2019, 'Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization from Complex Spectra', IEEE/ACM Transactions on Audio, Speech and Language Processing, pp. 244-254. https://doi.org/10.1109/TASLP.2018.2877465","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.ed.ac.uk:publications/7e177912-d04d-4d77-af2d-9592495f676c","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/8502065","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/7e177912-d04d-4d77-af2d-9592495f676c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/7e177912-d04d-4d77-af2d-9592495f676c","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nakashika, T, Takaki, S & Yamagishi, J 2019, 'Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization from Complex Spectra', IEEE/ACM Transactions on Audio, Speech and Language Processing, pp. 244-254. https://doi.org/10.1109/TASLP.2018.2877465","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3349790956","display_name":"Direct modeling of speech waveform using a DNN for text-to-speech synthesis","funder_award_id":"16K16096","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G497407216","display_name":"Speech Representation Using Emotion-Speaker Controllable Probabilistic Model Based on Extended Boltzmann Distribution","funder_award_id":"18K18069","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6954941931","display_name":"Communication System for Defending against Attacks of Media Clones","funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W189596042","https://openalex.org/W1522301498","https://openalex.org/W1666984270","https://openalex.org/W1902027874","https://openalex.org/W2010961394","https://openalex.org/W2028666306","https://openalex.org/W2043893894","https://openalex.org/W2049686551","https://openalex.org/W2060257243","https://openalex.org/W2091743772","https://openalex.org/W2120847449","https://openalex.org/W2133257461","https://openalex.org/W2135341757","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2141779515","https://openalex.org/W2145892079","https://openalex.org/W2150619194","https://openalex.org/W2154920538","https://openalex.org/W2161000554","https://openalex.org/W2163312093","https://openalex.org/W2165225968","https://openalex.org/W2252446102","https://openalex.org/W2294038178","https://openalex.org/W2342590538","https://openalex.org/W2471520273","https://openalex.org/W2475998840","https://openalex.org/W2519091744","https://openalex.org/W2746163980","https://openalex.org/W2749881488","https://openalex.org/W2752796333","https://openalex.org/W2919115771","https://openalex.org/W2963799213","https://openalex.org/W4289784446","https://openalex.org/W6607775107","https://openalex.org/W6631190155","https://openalex.org/W6637061625","https://openalex.org/W6679718588","https://openalex.org/W6679825673","https://openalex.org/W6680066585","https://openalex.org/W6680976990","https://openalex.org/W6684349851","https://openalex.org/W6691364839","https://openalex.org/W6697024540","https://openalex.org/W6743100201","https://openalex.org/W6743594052"],"related_works":["https://openalex.org/W2119341610","https://openalex.org/W4283272532","https://openalex.org/W2916681395","https://openalex.org/W2952018105","https://openalex.org/W2556473569","https://openalex.org/W4302433642","https://openalex.org/W1575733688","https://openalex.org/W2529583158","https://openalex.org/W2108438604","https://openalex.org/W2547523780"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,214,217],"novel":[4],"energy-based":[5],"probabilistic":[6],"distribution":[7,113],"that":[8,90,108,202],"represents":[9],"complex-valued":[10,23,29,39,105,166],"data":[11,112],"and":[12,62,98,123,135,145],"explains":[13],"how":[14],"to":[15,18,36],"apply":[16],"it":[17],"direct":[19],"feature":[20,154],"extraction":[21],"from":[22,142,192],"spectra.":[24],"The":[25],"proposed":[26,153],"model,":[27],"the":[28,46,53,55,58,71,91,104,111,115,152,157,161,169,179,189,193,203],"restricted":[30,48],"Boltzmann":[31,49],"machine":[32,50],"(CRBM),":[33],"is":[34,89],"designed":[35],"deal":[37],"with":[38],"visible":[40,61,106],"units":[41,64,69,107],"as":[42,211],"an":[43],"extension":[44],"of":[45,101,103,168],"well-known":[47],"(RBM).":[51],"Like":[52],"RBM,":[54,216],"CRBM":[56,92,158,204],"learns":[57],"relationships":[59],"between":[60,68,96],"hidden":[63],"without":[65],"having":[66],"connections":[67,95,181],"in":[70,114],"same":[72],"layer,":[73],"which":[74],"dramatically":[75],"improves":[76],"training":[77],"efficiency":[78],"by":[79],"using":[80,156,213],"Gibbs":[81],"sampling":[82],"or":[83],"contrastive":[84],"divergence.":[85],"Another":[86],"important":[87],"characteristic":[88],"also":[93,186],"has":[94],"real":[97],"imaginary":[99],"parts":[100],"each":[102],"help":[109],"represent":[110],"complex":[116,143,162,170,190],"domain.":[117],"In":[118,150],"speech":[119,198,207],"signal":[120],"processing,":[121],"classification":[122],"generation":[124],"features":[125,175,195],"are":[126,140,182],"often":[127],"based":[128],"on":[129],"amplitude":[130],"spectra":[131,163,191],"(e.g.,":[132],"MFCC,":[133],"cepstra,":[134],"mel-cepstra)":[136],"even":[137],"if":[138],"they":[139,146],"calculated":[141],"spectra,":[144],"ignore":[147],"phase":[148],"information.":[149],"contrast,":[151],"extractor":[155],"directly":[159],"encodes":[160],"(or":[164],"another":[165],"representation":[167,199,208],"spectra)":[171],"into":[172],"binary-valued":[173],"latent":[174,194],"(hidden":[176],"units).":[177],"Since":[178],"visible-hidden":[180],"undirected,":[183],"we":[184],"can":[185],"recover":[187],"(decode)":[188],"directly.":[196],"Our":[197],"experiments":[200],"demonstrated":[201],"outperformed":[205],"other":[206],"methods,":[209],"such":[210],"methods":[212],"conventional":[215],"mel-log":[218],"spectrum":[219],"approximate":[220],"decoder,":[221],"etc.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}