{"id":"https://openalex.org/W2394507897","doi":"https://doi.org/10.1109/icassp.2016.7472654","title":"Modeling spectral envelopes using deep conditional restricted Boltzmann machines for statistical parametric speech synthesis","display_name":"Modeling spectral envelopes using deep conditional restricted Boltzmann machines for statistical parametric speech synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2394507897","doi":"https://doi.org/10.1109/icassp.2016.7472654","mag":"2394507897"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472654","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/A5101874107","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-0741-4831"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059516164","display_name":"Ya-Jun Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ya-Jun Hu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R. China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101874107"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4285,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.77650558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"5125","last_page":"5129"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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":0.9919000267982483,"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/boltzmann-machine","display_name":"Boltzmann machine","score":0.8726236820220947},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7530363202095032},{"id":"https://openalex.org/keywords/restricted-boltzmann-machine","display_name":"Restricted Boltzmann machine","score":0.6981447339057922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6560598611831665},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6127227544784546},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5455784201622009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49613913893699646},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4900142252445221},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48090147972106934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.478158563375473},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4563766419887543},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.4372212886810303},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4064836800098419},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34708335995674133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2549246549606323},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0785817801952362}],"concepts":[{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.8726236820220947},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7530363202095032},{"id":"https://openalex.org/C199354608","wikidata":"https://www.wikidata.org/wiki/Q7316287","display_name":"Restricted Boltzmann machine","level":3,"score":0.6981447339057922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560598611831665},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6127227544784546},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5455784201622009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49613913893699646},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4900142252445221},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48090147972106934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.478158563375473},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4563766419887543},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.4372212886810303},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4064836800098419},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34708335995674133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2549246549606323},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0785817801952362},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472654","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1600722501","https://openalex.org/W1972420736","https://openalex.org/W1990505856","https://openalex.org/W2020024436","https://openalex.org/W2030637102","https://openalex.org/W2049686551","https://openalex.org/W2072128103","https://openalex.org/W2079337129","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2136922672","https://openalex.org/W2137782235","https://openalex.org/W2154920538","https://openalex.org/W2158164339","https://openalex.org/W2159528802","https://openalex.org/W4231109964","https://openalex.org/W6675380101","https://openalex.org/W6683128514","https://openalex.org/W6683640347","https://openalex.org/W7075637324"],"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/W4302433642","https://openalex.org/W2529583158","https://openalex.org/W2108438604","https://openalex.org/W2193475944","https://openalex.org/W2551541394"],"abstract_inverted_index":{"This":[0,152],"paper":[1],"proposes":[2],"a":[3,8,23,27,33,94],"spectral":[4,47,106,169],"modeling":[5],"method":[6,134,153],"using":[7],"deep":[9,28,56],"conditional":[10,34,44],"restricted":[11,35,160],"Boltzmann":[12,36,161],"machine":[13,37],"(DCRBM)":[14],"for":[15],"statistical":[16],"parametric":[17],"speech":[18,139],"synthesis.":[19],"In":[20],"this":[21],"method,":[22],"DCRBM,":[24],"which":[25,158],"combines":[26],"neural":[29],"network":[30,59],"(DNN)":[31],"with":[32,53,73],"(CRBM),":[38],"is":[39,62,101],"utilized":[40],"to":[41,164],"describe":[42],"the":[43,66,79,83,87,111,142,166],"distribution":[45,68],"of":[46,69,86,97,125,168],"envelopes":[48,107,170],"given":[49,122],"linguistic":[50,123],"features.":[51],"Compared":[52],"DNN":[54,80],"and":[55,82,92,118,148],"mixture":[57],"density":[58],"(DMDN),":[60],"DCRBM":[61,88,113],"better":[63],"at":[64,171],"describing":[65],"multimodal":[67],"high-dimensional":[70],"acoustic":[71],"features":[72,124],"cross-dimension":[74],"correlations.":[75],"At":[76,103],"training":[77],"stage,":[78],"part":[81,85],"CRBM":[84],"are":[89,108],"pre-trained":[90],"successively":[91],"then":[93],"unified":[95],"fine-tuning":[96],"all":[98],"model":[99,114,145,165],"parameters":[100],"conducted.":[102],"synthesis":[104,150],"time,":[105],"generated":[109],"from":[110],"estimated":[112],"by":[115],"iterative":[116],"sampling":[117],"dynamic-feature-constrained":[119],"parameter":[120],"generation":[121],"input":[126],"text.":[127],"Experimental":[128],"results":[129],"show":[130],"that":[131],"our":[132],"proposed":[133],"can":[135],"produce":[136],"more":[137],"natural":[138],"sounds":[140],"than":[141],"hidden":[143],"Markov":[144],"(HMM)-based,":[146],"DNN-based,":[147],"DMDN-based":[149],"methods.":[151],"also":[154],"outperforms":[155],"previous":[156],"work":[157],"adopts":[159],"machines":[162],"(RBM)":[163],"distributions":[167],"HMM":[172],"states.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}