{"id":"https://openalex.org/W2399853303","doi":"https://doi.org/10.1109/icassp.2016.7472733","title":"Gating recurrent mixture density networks for acoustic modeling in statistical parametric speech synthesis","display_name":"Gating recurrent mixture density networks for acoustic modeling in statistical parametric speech synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399853303","doi":"https://doi.org/10.1109/icassp.2016.7472733","mag":"2399853303"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472733","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/A5101868308","display_name":"Wenfu Wang","orcid":"https://orcid.org/0000-0003-1254-3910"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenfu Wang","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732438","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-1804-4012"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Interactive Digital Media Technology Research Center, Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101868308"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":3.4278,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9346973,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5520","last_page":"5524"},"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":0.9977999925613403,"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":0.9954000115394592,"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/parametric-statistics","display_name":"Parametric statistics","score":0.764851987361908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696049571037292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5235371589660645},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.5081467628479004},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.46119973063468933},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.42251232266426086},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4010496735572815},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2647808790206909},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12989699840545654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1060793399810791},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08793455362319946}],"concepts":[{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.764851987361908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696049571037292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5235371589660645},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.5081467628479004},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.46119973063468933},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.42251232266426086},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4010496735572815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2647808790206909},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12989699840545654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1060793399810791},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08793455362319946},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472733","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472733","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":[{"score":0.4000000059604645,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W156805311","https://openalex.org/W1499332833","https://openalex.org/W1499864241","https://openalex.org/W1524333225","https://openalex.org/W1576227399","https://openalex.org/W1578102511","https://openalex.org/W1579853615","https://openalex.org/W1600722501","https://openalex.org/W1736701665","https://openalex.org/W1924770834","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2102003408","https://openalex.org/W2102113734","https://openalex.org/W2107878631","https://openalex.org/W2129142580","https://openalex.org/W2133564696","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2157331557","https://openalex.org/W2294797155","https://openalex.org/W2397670047","https://openalex.org/W2963211739","https://openalex.org/W2964308564","https://openalex.org/W6629930100","https://openalex.org/W6634817459","https://openalex.org/W6696843773"],"related_works":["https://openalex.org/W2111813998","https://openalex.org/W18281484","https://openalex.org/W2045376368","https://openalex.org/W2027372234","https://openalex.org/W3033433517","https://openalex.org/W2112565040","https://openalex.org/W4287761163","https://openalex.org/W4229440744","https://openalex.org/W2621784762","https://openalex.org/W2079472785"],"abstract_inverted_index":{"Though":[0],"recurrent":[1,55,76],"neural":[2,68],"networks":[3],"(RNNs)":[4],"using":[5],"long":[6],"short-term":[7],"memory":[8],"(LSTM)":[9],"units":[10,126],"can":[11,112],"address":[12,63],"the":[13,19,25,37,74,108,123],"issue":[14],"of":[15,36,41],"long-span":[16],"dependencies":[17],"across":[18],"linguistic":[20],"inputs":[21],"and":[22,83,121,128],"have":[23],"achieved":[24],"state-of-the-art":[26],"performance":[27],"for":[28],"statistical":[29],"parametric":[30],"speech":[31,116],"synthesis":[32],"(SPSS),":[33],"another":[34],"limitation":[35],"intrinsic":[38],"uni-Gaussian":[39],"nature":[40],"mean":[42],"square":[43],"error":[44],"(MSE)":[45],"objective":[46],"function":[47],"still":[48],"remains.":[49],"This":[50],"paper":[51],"proposes":[52],"a":[53],"gating":[54,97,125],"mixture":[56],"density":[57],"network":[58,69],"(GRMDN)":[59],"architecture":[60,111],"to":[61],"jointly":[62],"these":[64],"two":[65,124],"problems":[66],"in":[67,99],"based":[70,101],"SPSS.":[71],"What's":[72],"more,":[73],"gated":[75],"unit":[77,98],"(GRU),":[78],"which":[79],"is":[80,91],"much":[81],"simpler":[82],"has":[84],"more":[85,114],"intelligible":[86],"work":[87],"mechanism":[88],"than":[89,117],"LSTM,":[90],"also":[92],"investigated":[93],"as":[94],"an":[95],"alternative":[96],"RNN":[100],"acoustic":[102],"modeling.":[103],"Experimental":[104],"results":[105],"show":[106,130],"that":[107],"proposed":[109],"GRMDN":[110],"synthesize":[113],"natural":[115],"its":[118],"MSE-trained":[119],"counterpart":[120],"both":[122],"(LSTM":[127],"GRU)":[129],"comparable":[131],"performance.":[132]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}