{"id":"https://openalex.org/W2102003408","doi":"https://doi.org/10.1109/icassp.2013.6639215","title":"Statistical parametric speech synthesis using deep neural networks","display_name":"Statistical parametric speech synthesis using deep neural networks","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2102003408","doi":"https://doi.org/10.1109/icassp.2013.6639215","mag":"2102003408"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639215","doi":"https://doi.org/10.1109/icassp.2013.6639215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639215","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2102003408"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471","observed_orcids":["https://orcid.org/0000-0002-8959-5471"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Google, USA","Google, Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691","observed_orcids":["https://orcid.org/0000-0002-2401-5691"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google, USA","Google, Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113452656","display_name":"Mike Schuster","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mike Schuster","raw_affiliation_strings":["Google, USA","Google, Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Mountain View, CA USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":40.7657,"has_fulltext":false,"cited_by_count":819,"citation_normalized_percentile":{"value":0.99945786,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7962","last_page":"7966"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/statistical-parametric-speech-synthesis","display_name":"statistical parametric speech synthesis","score":0.996999979019165},{"id":"https://openalex.org/keywords/deep-neural-network","display_name":"deep neural network","score":0.9869999885559082},{"id":"https://openalex.org/keywords/decision-tree","display_name":"decision tree","score":0.6660000085830688},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.7979999780654907},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.5490000247955322},{"id":"https://openalex.org/keywords/waveform-reconstruction","display_name":"waveform reconstruction","score":0.5820000171661377}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7897413969039917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.76009601354599},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6753268837928772},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6568033695220947},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5995689630508423},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5504841804504395},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5451977252960205},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5326122045516968},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4999096393585205},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4921223521232605},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4543328881263733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45258012413978577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32657065987586975},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14818784594535828},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07593926787376404},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639215","doi":"https://doi.org/10.1109/icassp.2013.6639215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639215","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.308.2194","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.308.2194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/external_content/untrusted_dlcp/research.google.com/en/us/pubs/archive/40837.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W4362787","https://openalex.org/W68089216","https://openalex.org/W80543058","https://openalex.org/W102093577","https://openalex.org/W344150399","https://openalex.org/W1512429158","https://openalex.org/W1600722501","https://openalex.org/W1861150963","https://openalex.org/W1882624840","https://openalex.org/W1964420823","https://openalex.org/W1994396704","https://openalex.org/W2000513720","https://openalex.org/W2029434926","https://openalex.org/W2039800941","https://openalex.org/W2042691334","https://openalex.org/W2048389584","https://openalex.org/W2072128103","https://openalex.org/W2093450784","https://openalex.org/W2093632031","https://openalex.org/W2093866254","https://openalex.org/W2095437083","https://openalex.org/W2106792148","https://openalex.org/W2117418893","https://openalex.org/W2120605154","https://openalex.org/W2120649056","https://openalex.org/W2123799894","https://openalex.org/W2129142580","https://openalex.org/W2131650634","https://openalex.org/W2143361917","https://openalex.org/W2150658333","https://openalex.org/W2150906086","https://openalex.org/W2154920538","https://openalex.org/W2158086337","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2170849167","https://openalex.org/W2184045248","https://openalex.org/W2228674556","https://openalex.org/W2395955767","https://openalex.org/W4231109964","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1502723613","https://openalex.org/W2400654494","https://openalex.org/W2134973740","https://openalex.org/W2408684684","https://openalex.org/W2965648961","https://openalex.org/W1990505856","https://openalex.org/W2406990556","https://openalex.org/W2255418810","https://openalex.org/W2952848210","https://openalex.org/W2511548894"],"abstract_inverted_index":{"Conventional":[0],"approaches":[1],"to":[2,16,33,64],"statistical":[3],"parametric":[4],"speech":[5,21,40],"synthesis":[6],"typically":[7],"use":[8,99],"decision":[9,60],"tree-clustered":[10],"context-dependent":[11],"hidden":[12],"Markov":[13],"models":[14],"(HMMs)":[15],"represent":[17],"probability":[18,31],"densities":[19,32],"of":[20,57,100,107,125],"parameters":[22,26],"given":[23],"texts.":[24],"Speech":[25],"are":[27,62],"generated":[28,46],"from":[29,44],"the":[30,45,101,108,115,119],"maximize":[34],"their":[35,90],"output":[36],"probabilities,":[37],"then":[38],"a":[39,55,79,96],"waveform":[41],"is":[42,50,76,93],"reconstructed":[43],"parameters.":[47,126],"This":[48,69],"approach":[49],"reasonably":[51],"effective":[52],"but":[53],"has":[54],"couple":[56],"limitations,":[58],"e.g.":[59],"trees":[61],"inefficient":[63],"model":[65],"complex":[66],"context":[67],"dependencies.":[68],"paper":[70],"examines":[71],"an":[72],"alternative":[73],"scheme":[74],"that":[75,114],"based":[77],"on":[78],"deep":[80],"neural":[81],"network":[82],"(DNN).":[83],"The":[84,98],"relationship":[85],"between":[86],"input":[87],"texts":[88],"and":[89],"acoustic":[91],"realizations":[92],"modeled":[94],"by":[95],"DNN.":[97],"DNN":[102],"can":[103],"address":[104],"some":[105],"limitations":[106],"conventional":[109],"approach.":[110],"Experimental":[111],"results":[112],"show":[113],"DNN-based":[116],"systems":[117,121],"outperformed":[118],"HMM-based":[120],"with":[122],"similar":[123],"numbers":[124]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":38},{"year":2022,"cited_by_count":52},{"year":2021,"cited_by_count":76},{"year":2020,"cited_by_count":101},{"year":2019,"cited_by_count":117},{"year":2018,"cited_by_count":109},{"year":2017,"cited_by_count":85},{"year":2016,"cited_by_count":93},{"year":2015,"cited_by_count":55},{"year":2014,"cited_by_count":29},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2016-06-24T00:00:00"}