{"id":"https://openalex.org/W2746163980","doi":"https://doi.org/10.21437/interspeech.2017-584","title":"Complex-Valued Restricted Boltzmann Machine for Direct Learning of Frequency Spectra","display_name":"Complex-Valued Restricted Boltzmann Machine for Direct Learning of Frequency Spectra","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2746163980","doi":"https://doi.org/10.21437/interspeech.2017-584","mag":"2746163980"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","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":true,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["University of Electro-Communications, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"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"],"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]},{"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":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041887072"],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":1.6643,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85379149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4021","last_page":"4025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9972000122070312,"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":0.7738564014434814},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.7021189332008362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6254048347473145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.55506432056427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49600109457969666},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49097779393196106},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47034481167793274},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.41117390990257263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36174869537353516},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34899652004241943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19983357191085815}],"concepts":[{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.7738564014434814},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.7021189332008362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6254048347473145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.55506432056427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49600109457969666},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49097779393196106},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47034481167793274},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.41117390990257263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36174869537353516},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34899652004241943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19983357191085815},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-584","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nakashika, T, Takaki, S & Yamagishi, J 2017, Complex-valued restricted Boltzmann machine for direct learning of frequency spectra. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 4021-4025, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-584","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/complexvalued-restricted-boltzmann-machine-for-direct-learning-of-frequency-spectra(20649c1e-26f5-4fdf-90d1-2aa0750f0b30).html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/20649c1e-26f5-4fdf-90d1-2aa0750f0b30","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Nakashika, T, Takaki, S & Yamagishi, J 2017, Complex-valued restricted Boltzmann machine for direct learning of frequency spectra. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 4021-4025, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-584","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W189596042","https://openalex.org/W1902027874","https://openalex.org/W2028666306","https://openalex.org/W2060257243","https://openalex.org/W2133257461","https://openalex.org/W2136922672","https://openalex.org/W2136936677","https://openalex.org/W2141779515","https://openalex.org/W2161000554","https://openalex.org/W2163312093","https://openalex.org/W2165225968","https://openalex.org/W2475998840"],"related_works":["https://openalex.org/W4283272532","https://openalex.org/W2952018105","https://openalex.org/W2119341610","https://openalex.org/W2916681395","https://openalex.org/W2556473569","https://openalex.org/W2193475944","https://openalex.org/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2108438604","https://openalex.org/W2551541394"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,11,52,55,57,144],"new":[6,124],"energy-based":[7],"probabilistic":[8],"model":[9,125],"where":[10,130],"restricted":[12],"Boltzmann":[13],"machine":[14],"(RBM)":[15],"is":[16,96,153],"extended":[17],"to":[18,75,88,154],"deal":[19],"with":[20],"complex-valued":[21,83,94,120,136],"visible":[22,32,42,73,137,166],"units.":[23],"The":[24],"RBM":[25,128],"that":[26,176],"automatically":[27],"learns":[28],"the":[29,41,44,67,72,89,114,119,123,131,135,140,151,165,169,177,195],"relationships":[30],"between":[31,157],"units":[33,36,74,138,142,167],"and":[34,81,110,159],"hidden":[35,45,141],"(but":[37],"without":[38,188],"connections":[39,156],"in":[40],"or":[43,79,192],"units)":[46],"has":[47],"been":[48],"widely":[49],"used":[50,98],"as":[51],"feature":[53],"extractor,":[54],"generator,":[56],"classifier,":[58],"pre-training":[59],"of":[60,104,117,134,150,162,164,185],"deep":[61],"neural":[62],"networks,":[63],"etc.":[64],"However,":[65],"all":[66],"conventional":[68,170],"RBMs":[69],"have":[70,155],"assumed":[71],"be":[76,86],"either":[77],"binary-valued":[78],"real-valued,":[80],"therefore":[82],"data":[84,95],"cannot":[85],"fed":[87],"RBM.<br/><br/>In":[90],"various":[91],"applications,":[92],"however,":[93],"frequently":[97],"such":[99,118],"examples":[100],"include":[101],"complex":[102,183],"spectra":[103,184],"speech,":[105],"fMRI":[106],"images,":[107],"wireless":[108],"signals,":[109],"acoustic":[111],"intensity.":[112],"For":[113],"direct":[115],"learning":[116],"data,":[121],"we<br/>define":[122],"called":[126],"\u201ccomplex-valued":[127],"(CRBM)\u201d":[129],"conditional":[132],"probability":[133],"given":[139],"forms":[143],"complex-Gaussian":[145],"distribution.":[146],"Another":[147],"important":[148],"characteristic":[149],"CRBM":[152,179],"real":[158],"imaginary":[160,190],"parts":[161],"each":[163],"unlike":[168],"real-valued":[171],"RBM.":[172],"Our":[173],"experiments":[174],"demonstrated":[175],"proposed":[178],"can":[180],"directly":[181],"encode":[182],"speech":[186],"signals":[187],"decoupling":[189],"number":[191],"phase":[193],"from":[194],"complex-value":[196],"data.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}