{"id":"https://openalex.org/W2794838827","doi":"https://doi.org/10.1109/lsp.2018.2819886","title":"Statistical Parametric Speech Synthesis Using Generalized Distillation Framework","display_name":"Statistical Parametric Speech Synthesis Using Generalized Distillation Framework","publication_year":2018,"publication_date":"2018-03-29","ids":{"openalex":"https://openalex.org/W2794838827","doi":"https://doi.org/10.1109/lsp.2018.2819886","mag":"2794838827"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2018.2819886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2819886","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","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/A5002028345","display_name":"Zheng-Chen Liu","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":true,"raw_author_name":"Zheng-Chen Liu","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"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":"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, China"],"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/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, China"],"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":3,"corresponding_author_ids":["https://openalex.org/A5002028345"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.9773,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81301408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":"5","first_page":"695","last_page":"699"},"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":0.9966999888420105,"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":0.9933000206947327,"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":0.8001480102539062},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7019922733306885},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6655859351158142},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5872558355331421},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.57419753074646},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5728067755699158},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5267079472541809},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5079150795936584},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5063482522964478},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.45730072259902954},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4496937692165375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4451425075531006},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4180111885070801},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4156171977519989},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3919842541217804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09673073887825012},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08855322003364563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001480102539062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7019922733306885},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6655859351158142},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5872558355331421},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.57419753074646},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5728067755699158},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5267079472541809},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5079150795936584},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5063482522964478},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.45730072259902954},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4496937692165375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4451425075531006},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4180111885070801},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4156171977519989},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3919842541217804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09673073887825012},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08855322003364563},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2018.2819886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2018.2819886","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5617169040","display_name":null,"funder_award_id":"2016YFB1001303","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"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}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1589867908","https://openalex.org/W1821462560","https://openalex.org/W1899504021","https://openalex.org/W1926768285","https://openalex.org/W1982854652","https://openalex.org/W2008120082","https://openalex.org/W2043003570","https://openalex.org/W2064675550","https://openalex.org/W2067562626","https://openalex.org/W2094035326","https://openalex.org/W2102003408","https://openalex.org/W2117130368","https://openalex.org/W2129142580","https://openalex.org/W2132733106","https://openalex.org/W2135707066","https://openalex.org/W2150355110","https://openalex.org/W2154920538","https://openalex.org/W2173379916","https://openalex.org/W2231075402","https://openalex.org/W2253986341","https://openalex.org/W2277581165","https://openalex.org/W2294797155","https://openalex.org/W2508425411","https://openalex.org/W2512865187","https://openalex.org/W2517736208","https://openalex.org/W2598638573","https://openalex.org/W2613360356","https://openalex.org/W2697504846","https://openalex.org/W2747525721","https://openalex.org/W4293390340","https://openalex.org/W6631636882","https://openalex.org/W6635242571","https://openalex.org/W6638523607","https://openalex.org/W6675380101","https://openalex.org/W6685316698","https://openalex.org/W6689608924","https://openalex.org/W6695138777","https://openalex.org/W6696843773","https://openalex.org/W6725784280","https://openalex.org/W6735509194","https://openalex.org/W6743014239"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W4298287631","https://openalex.org/W2294335174","https://openalex.org/W2953061907","https://openalex.org/W2097963413","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"an":[3],"improved":[4],"statistical":[5],"parametric":[6],"speech":[7,150],"synthesis":[8],"(SPSS)":[9],"method":[10,136],"which":[11,69,103,117],"utilizes":[12],"auxiliary":[13,79],"information":[14],"for":[15,110],"acoustic":[16,25,35,44,99,108,142,154],"modeling":[17,155],"under":[18],"generalized":[19],"distillation":[20],"framework.":[21],"In":[22,39],"conventional":[23,94,152],"SPSS,":[24],"models":[26],"are":[27,50,55],"trained":[28],"using":[29],"context":[30],"features":[31,36,80,83],"as":[32,37,105,124],"input":[33,95],"and":[34,48,96,145],"output.":[38],"our":[40],"proposed":[41],"method,":[42],"two":[43],"models,":[45],"so-called":[46],"teacher":[47,123],"student,":[49,102],"involved.":[51],"Both":[52],"of":[53,86,98,121,127,141],"them":[54],"recurrent":[56],"neural":[57],"networks":[58],"(RNN)":[59],"with":[60,75,156],"bidirectional":[61],"long":[62],"short-term":[63],"memory":[64],"(BLSTM)":[65],"units.":[66],"The":[67,101],"teacher,":[68],"aims":[70],"to":[71,92],"provide":[72],"the":[73,93,106,119,122,125],"student":[74],"additional":[76],"knowledge,":[77],"employs":[78],"(e.g.,":[81],"articulatory":[82],"or":[84,158],"spectra":[85],"short-time":[87],"Fourier":[88],"transform)":[89],"in":[90],"addition":[91],"output":[97],"models.":[100],"serves":[104],"final":[107],"model":[109],"synthesis,":[111],"adopts":[112],"a":[113],"multitask":[114,159],"learning":[115],"architecture":[116],"uses":[118],"outcome":[120],"target":[126],"its":[128],"secondary":[129],"task.":[130],"Experimental":[131],"results":[132],"show":[133],"that":[134],"this":[135],"can":[137],"achieve":[138],"better":[139],"accuracy":[140],"feature":[143],"prediction":[144],"produce":[146],"more":[147],"natural":[148],"synthetic":[149],"than":[151],"BLSTM-RNN-based":[153],"single-task":[157],"learning.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}