{"id":"https://openalex.org/W2595110011","doi":"https://doi.org/10.1109/icassp.2017.7953087","title":"An autoregressive recurrent mixture density network for parametric speech synthesis","display_name":"An autoregressive recurrent mixture density network for parametric speech synthesis","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2595110011","doi":"https://doi.org/10.1109/icassp.2017.7953087","mag":"2595110011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Graduate University for Advanced Studies, Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate University for Advanced Studies, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, 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/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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"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"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, U.K","Graduate University for Advanced Studies, Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Graduate University for Advanced Studies, Japan","institution_ids":["https://openalex.org/I200475212"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4895","last_page":"4899"},"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":0.9991000294685364,"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":0.9987999796867371,"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/autoregressive-model","display_name":"Autoregressive model","score":0.9015376567840576},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048183083534241},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5689416527748108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5395442843437195},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5395218133926392},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5187797546386719},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.49801158905029297},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45506617426872253},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4417990744113922},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43434953689575195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43342214822769165},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4123801589012146},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2476295828819275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17719754576683044},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09457945823669434}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.9015376567840576},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048183083534241},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5689416527748108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5395442843437195},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5395218133926392},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5187797546386719},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.49801158905029297},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45506617426872253},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4417990744113922},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43434953689575195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43342214822769165},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4123801589012146},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2476295828819275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17719754576683044},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09457945823669434},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7953087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/09eaa479-9c18-4189-a418-a867f3622990","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/09eaa479-9c18-4189-a418-a867f3622990","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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W304834817","https://openalex.org/W566667199","https://openalex.org/W1511967608","https://openalex.org/W1576227399","https://openalex.org/W1579853615","https://openalex.org/W1584826989","https://openalex.org/W1979449467","https://openalex.org/W1979871770","https://openalex.org/W1987992317","https://openalex.org/W1990505856","https://openalex.org/W2000513720","https://openalex.org/W2020024436","https://openalex.org/W2024083195","https://openalex.org/W2049686551","https://openalex.org/W2099932314","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2112656927","https://openalex.org/W2144499799","https://openalex.org/W2294797155","https://openalex.org/W2395849284","https://openalex.org/W2403471241","https://openalex.org/W2405144467","https://openalex.org/W2917245127","https://openalex.org/W2964301388","https://openalex.org/W6630772573","https://openalex.org/W6634817459","https://openalex.org/W6675380101","https://openalex.org/W6676943934","https://openalex.org/W6677973343","https://openalex.org/W6696843773","https://openalex.org/W6713400016"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W2049352309","https://openalex.org/W4249887698","https://openalex.org/W4206659980","https://openalex.org/W2990594878"],"abstract_inverted_index":{"Neural-network-based":[0],"generative":[1],"models,":[2],"such":[3],"as":[4],"mixture":[5,25],"density":[6,26],"networks,":[7],"are":[8],"potential":[9],"solutions":[10],"for":[11],"speech":[12,125],"synthesis.":[13],"In":[14,88],"this":[15,19,64],"paper":[16],"we":[17],"follow":[18],"path":[20],"and":[21,103,123],"propose":[22],"a":[23,30,70],"recurrent":[24],"network":[27],"that":[28,42,63,72,112],"incorporates":[29],"trainable":[31],"autoregressive":[32,39,65],"model.":[33,140],"An":[34],"advantage":[35],"of":[36,78,98],"incorporating":[37],"an":[38],"model":[40,66,115],"is":[41],"the":[43,55,74,79,85,89,94,99,113,120],"time":[44],"dependency":[45],"within":[46],"acoustic":[47,81],"feature":[48,82,101],"trajectories":[49,83,102],"can":[50],"be":[51,69],"modeled":[52],"without":[53],"using":[54],"conventional":[56],"dynamic":[57,133],"features.":[58],"More":[59],"interestingly,":[60],"experiments":[61],"show":[62,111],"learns":[67],"to":[68],"filter":[71],"emphasizes":[73],"high":[75],"frequency":[76,96],"components":[77,97],"target":[80],"in":[84,138],"training":[86,121],"stage.":[87],"synthesis":[90],"stage,":[91],"it":[92],"boosts":[93],"low":[95],"generated":[100,124],"hence":[104],"increases":[105],"their":[106],"global":[107],"variance.":[108],"Experimental":[109],"results":[110],"proposed":[114],"achieved":[116],"higher":[117],"likelihood":[118],"on":[119],"data":[122],"with":[126],"better":[127],"quality":[128],"than":[129],"other":[130],"models":[131],"when":[132],"features":[134],"were":[135],"not":[136],"utilized":[137],"any":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}