{"id":"https://openalex.org/W2783657448","doi":"https://doi.org/10.1109/taslp.2018.2791804","title":"Extracting Spectral Features Using Deep Autoencoders With Binary Distributed Hidden Units for Statistical Parametric Speech Synthesis","display_name":"Extracting Spectral Features Using Deep Autoencoders With Binary Distributed Hidden Units for Statistical Parametric Speech Synthesis","publication_year":2018,"publication_date":"2018-01-10","ids":{"openalex":"https://openalex.org/W2783657448","doi":"https://doi.org/10.1109/taslp.2018.2791804","mag":"2783657448"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2791804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2791804","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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, China"],"raw_orcid":"https://orcid.org/0000-0003-0624-6119","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","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, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.9265,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81316147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"4","first_page":"713","last_page":"724"},"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":0.9980000257492065,"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":0.9934999942779541,"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":0.7211502194404602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6372426748275757},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5947179198265076},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5871598720550537},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5812894105911255},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5278757810592651},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5258791446685791},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5163737535476685},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.515096127986908},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5088015198707581},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5068710446357727},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4965882897377014},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48759832978248596},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4248066842556},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.20982852578163147},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1479186713695526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211502194404602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6372426748275757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5947179198265076},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5871598720550537},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5812894105911255},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5278757810592651},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5258791446685791},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5163737535476685},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.515096127986908},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5088015198707581},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5068710446357727},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4965882897377014},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48759832978248596},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4248066842556},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.20982852578163147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1479186713695526},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2791804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2791804","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G2045408545","display_name":null,"funder_award_id":"2016QY02D0401","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3256020066","display_name":null,"funder_award_id":"WK2350000001","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8406824694","display_name":null,"funder_award_id":"U1636201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1600722501","https://openalex.org/W1813659000","https://openalex.org/W2042691334","https://openalex.org/W2045158511","https://openalex.org/W2049036695","https://openalex.org/W2049686551","https://openalex.org/W2100495367","https://openalex.org/W2102003408","https://openalex.org/W2108674328","https://openalex.org/W2111194146","https://openalex.org/W2111284386","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2137782235","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2163922914","https://openalex.org/W2166823384","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2255418810","https://openalex.org/W2274854232","https://openalex.org/W2292984643","https://openalex.org/W2294797155","https://openalex.org/W2395849284","https://openalex.org/W2400679416","https://openalex.org/W2403471241","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2608305796","https://openalex.org/W2618530766","https://openalex.org/W2666408839","https://openalex.org/W2913932916","https://openalex.org/W2949382160","https://openalex.org/W3123963976","https://openalex.org/W6601785968","https://openalex.org/W6675380101","https://openalex.org/W6676044216","https://openalex.org/W6676358011","https://openalex.org/W6684683940","https://openalex.org/W6696843773","https://openalex.org/W6697163159","https://openalex.org/W6732429163","https://openalex.org/W6736620556","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"This":[0,102],"paper":[1,103],"presents":[2],"a":[3,183],"spectral":[4,146,156,162,166],"feature":[5,52,147,207],"extraction":[6],"method":[7,110],"using":[8,173],"deep":[9,132],"autoencoders":[10],"(DAEs)":[11],"with":[12],"binary":[13,77],"distributed":[14],"hidden":[15,63,71,118],"units":[16,72,119],"(BDAE)":[17],"for":[18,54,138],"statistical":[19],"parametric":[20],"speech":[21,198],"synthesis":[22],"(SPSS).":[23],"Conventional":[24],"DAEs":[25,45,74,211],"are":[26,92],"trained":[27],"to":[28,75,114,169],"minimize":[29],"the":[30,58,70,81,95,115,142,160,179],"error":[31],"of":[32,44,60,62,73,94,98,117,144,182,196],"reconstructing":[33],"raw":[34],"features.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"investigate":[40],"another":[41],"important":[42],"property":[43],"that":[46,68,152,191],"may":[47,78],"influence":[48],"their":[49],"performances":[50,143],"as":[51,135,210],"extractors":[53],"regression":[55],"tasks,":[56],"i.e.,":[57],"degree":[59],"binarization":[61],"units.":[64],"Our":[65,128],"analysis":[66],"shows":[67],"making":[69],"be":[76],"help":[79],"alleviate":[80],"over-smoothing":[82],"effect":[83],"caused":[84],"by":[85,111,158],"acoustic":[86,136],"modeling":[87],"and":[88,123,140,186,202,212],"parameter":[89],"generation,":[90],"which":[91],"one":[93],"main":[96],"deficiencies":[97],"current":[99],"SPSS":[100,139],"systems.":[101],"further":[104],"proposes":[105],"an":[106,187],"effective":[107],"BDAE":[108],"training":[109,122],"adding":[112],"noise":[113],"input":[116],"during":[120],"model":[121],"applying":[124],"DBN-based":[125],"pretraining":[126],"strategies.":[127],"experiments":[129],"adopt":[130],"feedforward":[131],"neural":[133,204],"networks":[134],"models":[137],"compare":[141],"different":[145],"extractors.":[148],"Experimental":[149],"results":[150],"show":[151],"when":[153],"extracting":[154],"low-dimensional":[155],"features":[157,163],"BDAEs,":[159],"predicted":[161],"can":[164],"reconstruct":[165],"envelopes":[167],"closer":[168],"natural":[170],"samples":[171],"than":[172,199],"conventional":[174,200],"DAEs.":[175],"Subjective":[176],"evaluations":[177],"on":[178],"synthetic":[180,197],"voices":[181],"Chinese":[184],"speaker":[185,189],"English":[188],"demonstrate":[190],"BDAEs":[192],"achieve":[193],"better":[194],"naturalness":[195],"mel-cepstra":[201],"other":[203],"network":[205],"based":[206],"extractors,":[208],"such":[209],"DBNs.":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}